Triple

T12573245
Position Surface form Disambiguated ID Type / Status
Subject Fort Kochi E295655 entity
Predicate hasLandmark P105 FINISHED
Object Dutch Cemetery E628184 NE FINISHED

How this triple was built (2 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: Dutch Cemetery | Statement: [Fort Kochi, hasLandmark, Dutch Cemetery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dutch Cemetery
Context triple: [Fort Kochi, hasLandmark, Dutch Cemetery]
  • A. Zorgvlied Cemetery
    Zorgvlied Cemetery is a well-known Dutch cemetery near Amsterdam, noted as the final resting place of many prominent figures including Nobel laureate Christiaan Eijkman.
  • B. Dutch cemetery chosen
    The Dutch cemetery in Bogor is a historic colonial-era burial ground where many Dutch officials and residents from the period of the Dutch East Indies are interred.
  • C. Ekeren cemetery
    Ekeren cemetery is a burial ground located in the district of Ekeren in Antwerp, Belgium.
  • D. Dieweg Cemetery
    Dieweg Cemetery is a historic and overgrown burial ground in Uccle, Brussels, known for its atmospheric decay, diverse funerary art, and notable graves.
  • E. Trumpeldor Cemetery
    Trumpeldor Cemetery is a historic Jewish burial ground in central Tel Aviv, Israel, known as the resting place of many prominent Zionist leaders, writers, and cultural figures.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d954a52c788190beac128a97e34dc1 completed April 10, 2026, 7:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f65eb8ec888190b46a0b48840efd20 completed May 2, 2026, 8:29 p.m.
Created at: April 8, 2026, 11:50 p.m.