Triple

T5595396
Position Surface form Disambiguated ID Type / Status
Subject Edificio Metrópolis E146984 entity
Predicate previousRoofStatue P64961 FINISHED
Object phoenix with Ganymede
Phoenix with Ganymede is a sculptural group depicting the mythological youth Ganymede with a phoenix, formerly crowning the roof of Madrid’s iconic Edificio Metrópolis.
E529466 NE FINISHED

How this triple was built (5 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: phoenix with Ganymede | Statement: [Edificio Metrópolis, previousRoofStatue, phoenix with Ganymede]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: phoenix with Ganymede
Context triple: [Edificio Metrópolis, previousRoofStatue, phoenix with Ganymede]
  • A. Phénix
    Phénix is the French Air and Space Force’s designation for its Airbus A330 MRTT multirole tanker and transport aircraft.
  • B. The Phoenix
    The Phoenix is an Old English Christian allegorical poem that uses the mythical bird’s cycle of death and rebirth to symbolize spiritual resurrection and eternal life.
  • C. Gemini 2.0
    Gemini 2.0 is a major updated release of Google’s multimodal AI model family, designed to provide more powerful and versatile capabilities across text, code, image, and other modalities.
  • D. PHENIX
    PHENIX is a major nuclear physics experiment at the Relativistic Heavy Ion Collider designed to study the properties of quark-gluon plasma and the strong interaction under extreme conditions.
  • E. Velorama
    Velorama is a Dutch national bicycle museum in Nijmegen that showcases the history and development of bicycles through an extensive collection of historic bikes and related artifacts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: phoenix with Ganymede
Triple: [Edificio Metrópolis, previousRoofStatue, phoenix with Ganymede]
Generated description
Phoenix with Ganymede is a sculptural group depicting the mythological youth Ganymede with a phoenix, formerly crowning the roof of Madrid’s iconic Edificio Metrópolis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: phoenix with Ganymede
Target entity description: Phoenix with Ganymede is a sculptural group depicting the mythological youth Ganymede with a phoenix, formerly crowning the roof of Madrid’s iconic Edificio Metrópolis.
  • A. Phénix
    Phénix is the French Air and Space Force’s designation for its Airbus A330 MRTT multirole tanker and transport aircraft.
  • B. The Phoenix
    The Phoenix is an Old English Christian allegorical poem that uses the mythical bird’s cycle of death and rebirth to symbolize spiritual resurrection and eternal life.
  • C. Gemini 2.0
    Gemini 2.0 is a major updated release of Google’s multimodal AI model family, designed to provide more powerful and versatile capabilities across text, code, image, and other modalities.
  • D. PHENIX
    PHENIX is a major nuclear physics experiment at the Relativistic Heavy Ion Collider designed to study the properties of quark-gluon plasma and the strong interaction under extreme conditions.
  • E. Velorama
    Velorama is a Dutch national bicycle museum in Nijmegen that showcases the history and development of bicycles through an extensive collection of historic bikes and related artifacts.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousRoofStatue
Context triple: [Edificio Metrópolis, previousRoofStatue, phoenix with Ganymede]
  • A. statueName
    Indicates that a statue has a specific name or title associated with it.
  • B. sculptorOfFrontStatue
    Indicates that one entity is the sculptor who created the statue located at the front of another entity (such as a building or site).
  • C. positionOfStatue
    Indicates the spatial location where a statue is situated or placed.
  • D. statueHeight
    Indicates the height measurement of a statue in some specified unit.
  • E. hasRockCarvingsFrom
    Indicates that something contains or features rock carvings that originate from a specified source, place, or period.
  • F. None of above. chosen

Provenance (7 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c009043d648190a7af89698ccf1e3e completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020be029881908c5586838382c8f2 completed March 22, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0286eaa2881909cbb0bb20f4987fe completed March 22, 2026, 5:35 p.m.
NEDg Description generation batch_69c037fca93881908d4d7403bfb1f866 completed March 22, 2026, 6:42 p.m.
NED2 Entity disambiguation (via description) batch_69c03898327c8190bd3b889bd7663003 completed March 22, 2026, 6:44 p.m.
PD Predicate disambiguation batch_69c01b1890ec8190b9e6fa488792e4d4 completed March 22, 2026, 4:38 p.m.
PDg Predicate description generation batch_69c01f4032408190a4f0d2eb21ebd870 completed March 22, 2026, 4:56 p.m.
Created at: March 22, 2026, 3:38 p.m.