Triple

T3720483
Position Surface form Disambiguated ID Type / Status
Subject Galilean campaign of Vespasian E81625 entity
Predicate capturedCity P8411 FINISHED
Object Gamla
Gamla was an ancient Jewish stronghold on the Golan Heights, known for its dramatic siege and destruction by Roman forces during the First Jewish–Roman War.
 E381200 NE FINISHED

How this triple was built (4 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: Gamla | Statement: [Galilean campaign of Vespasian, capturedCity, Gamla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gamla
Context triple: [Galilean campaign of Vespasian, capturedCity, Gamla]
  • A. Djursholm
    Djursholm is an affluent suburban district of Stockholm, Sweden, known for its villas, garden-city planning, and status as one of the country’s wealthiest residential areas.
  • B. Oldambt
    Oldambt is a municipality in the northeast of the Netherlands, known for its reclaimed lake Oldambtmeer and its agricultural landscapes.
  • C. Märsta
    Märsta is a town in Stockholm County, Sweden, known as a residential and transport hub near Stockholm Arlanda Airport.
  • D. Hjulsta
    Hjulsta is a suburb in northwestern Stockholm, Sweden, known for being the terminus of one of the Stockholm metro lines.
  • E. Gärdet
    Gärdet is a large open parkland and residential area in central Stockholm, known for its green spaces, outdoor activities, and functionalist-era architecture.
  • 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: Gamla
Triple: [Galilean campaign of Vespasian, capturedCity, Gamla]
Generated description
Gamla was an ancient Jewish stronghold on the Golan Heights, known for its dramatic siege and destruction by Roman forces during the First Jewish–Roman War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gamla
Target entity description: Gamla was an ancient Jewish stronghold on the Golan Heights, known for its dramatic siege and destruction by Roman forces during the First Jewish–Roman War.
  • A. Djursholm
    Djursholm is an affluent suburban district of Stockholm, Sweden, known for its villas, garden-city planning, and status as one of the country’s wealthiest residential areas.
  • B. Oldambt
    Oldambt is a municipality in the northeast of the Netherlands, known for its reclaimed lake Oldambtmeer and its agricultural landscapes.
  • C. Märsta
    Märsta is a town in Stockholm County, Sweden, known as a residential and transport hub near Stockholm Arlanda Airport.
  • D. Hjulsta
    Hjulsta is a suburb in northwestern Stockholm, Sweden, known for being the terminus of one of the Stockholm metro lines.
  • E. Gärdet
    Gärdet is a large open parkland and residential area in central Stockholm, known for its green spaces, outdoor activities, and functionalist-era architecture.
  • F. None of above. chosen

Provenance (5 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_69ad8b1b7ef081908d2d381bbf54985a completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adca9b5ca8819094299fffc02606ce completed March 8, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4ce184c9c8190813ce589c48007c1 completed March 14, 2026, 2:55 a.m.
NEDg Description generation batch_69b4ce9188288190a354d747ade5043b completed March 14, 2026, 2:57 a.m.
NED2 Entity disambiguation (via description) batch_69b4cefbf6f081909aed20f8c455d5b8 completed March 14, 2026, 2:59 a.m.
Created at: March 8, 2026, 3:34 p.m.