Triple

T8010172
Position Surface form Disambiguated ID Type / Status
Subject Thomas Kostura E186467 entity
Predicate marriagePerformedIn P27490 FINISHED
Object New York E550 NE FINISHED

How this triple was built (3 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: New York | Statement: [Thomas Kostura, marriagePerformedIn, New York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New York
Context triple: [Thomas Kostura, marriagePerformedIn, New York]
  • A. New York chosen
    New York is a populous and economically significant U.S. state known for New York City, a global center of finance, culture, and media.
  • B. New York City
    New York City is the largest city in the United States, a global center of finance, culture, media, and technology.
  • C. Washington, New York
    Washington, New York is a rural town in Dutchess County known for its historic hamlet of Millbrook, scenic landscapes, and equestrian and agricultural heritage.
  • D. NYC
    NYC is a historic American railroad company that operated major passenger and freight services across the northeastern and midwestern United States.
  • E. Manhattan
    The Manhattan is a classic whiskey-based cocktail, traditionally made with rye or bourbon, sweet vermouth, and bitters, and typically served stirred and garnished with a cherry.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: marriagePerformedIn
Context triple: [Thomas Kostura, marriagePerformedIn, New York]
  • A. marriageLocation chosen
    Indicates the place where a marriage ceremony or legal union between two people took place.
  • B. betrothalOrMarriagePlace
    Indicates the location where a betrothal or marriage event takes place.
  • C. marriageDocumentedIn
    Indicates that a marriage event is recorded or evidenced in a specific document or source.
  • D. marriageContractConductedBy
    Indicates that a specific marriage contract or ceremony is formally carried out, officiated, or administered by a particular agent or authority.
  • E. marriageResolvedBy
    Indicates that a marital relationship between two parties has been formally concluded or dissolved through a specific resolving action or process (e.g., divorce, annulment).
  • F. None of above.

Provenance (4 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_69ca82abaffc8190ab8af79cdbc31ab3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3d70caf8819090a9f98025470c0d completed March 31, 2026, 3:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc63552ec8190bbcae99d48b5f763 completed April 2, 2026, 1:28 a.m.
PD Predicate disambiguation batch_69cb048c9f488190b4fb8917a9c21bc5 completed March 30, 2026, 11:17 p.m.
Created at: March 30, 2026, 5:19 p.m.