Triple

T7053427
Position Surface form Disambiguated ID Type / Status
Subject Gornji Grad E164025 entity
Predicate contains P35 FINISHED
Object Stone Gate
Stone Gate is a historic medieval city gate in Zagreb’s Upper Town, renowned as a religious shrine and one of the city’s most iconic landmarks.
E640695 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: Stone Gate | Statement: [Gornji Grad, contains, Stone Gate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stone Gate
Context triple: [Gornji Grad, contains, Stone Gate]
  • A. Valley Gates
    Valley Gates is a notable entrance area within Franklin Park in Boston, serving as one of the park’s key access points and landscape features.
  • B. Sainyar Gate
    Sainyar Gate is one of the historic entrance gates of Jhansi Fort, associated with the fort’s defensive architecture and its role in the 1857 Indian Rebellion.
  • C. Orpen Gate
    Orpen Gate is one of the main western entrances to South Africa’s Kruger National Park, providing access to popular wildlife viewing areas and rest camps.
  • D. Tabor Gate
    Tabor Gate is a historic entrance gate forming part of the medieval fortifications of the Vyšehrad complex in Prague.
  • E. Foog’s Gate
    Foog’s Gate is a historic entrance within Edinburgh Castle, serving as one of the main access points to the fortress complex.
  • 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: Stone Gate
Triple: [Gornji Grad, contains, Stone Gate]
Generated description
Stone Gate is a historic medieval city gate in Zagreb’s Upper Town, renowned as a religious shrine and one of the city’s most iconic landmarks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stone Gate
Target entity description: Stone Gate is a historic medieval city gate in Zagreb’s Upper Town, renowned as a religious shrine and one of the city’s most iconic landmarks.
  • A. Valley Gates
    Valley Gates is a notable entrance area within Franklin Park in Boston, serving as one of the park’s key access points and landscape features.
  • B. Sainyar Gate
    Sainyar Gate is one of the historic entrance gates of Jhansi Fort, associated with the fort’s defensive architecture and its role in the 1857 Indian Rebellion.
  • C. Orpen Gate
    Orpen Gate is one of the main western entrances to South Africa’s Kruger National Park, providing access to popular wildlife viewing areas and rest camps.
  • D. Tabor Gate
    Tabor Gate is a historic entrance gate forming part of the medieval fortifications of the Vyšehrad complex in Prague.
  • E. Foog’s Gate
    Foog’s Gate is a historic entrance within Edinburgh Castle, serving as one of the main access points to the fortress complex.
  • 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_69c68861678881909961ddf4d779f750 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e265ea348190a9bd3807c0d605d8 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7944535bc819086b7648d95b81e37 completed March 28, 2026, 8:41 a.m.
NEDg Description generation batch_69c7968ffb8881908e2d2138e114a1ba completed March 28, 2026, 8:51 a.m.
NED2 Entity disambiguation (via description) batch_69c796f045d88190aa5d26899333013c completed March 28, 2026, 8:53 a.m.
Created at: March 27, 2026, 2:37 p.m.