Triple

T5401447
Position Surface form Disambiguated ID Type / Status
Subject Marvel Entertainment E120786 entity
Predicate headquartersLocation P62 FINISHED
Object New York E550 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: New York | Statement: [Marvel Entertainment, headquartersLocation, New York]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New York
Context triple: [Marvel Entertainment, headquartersLocation, 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.

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_69bd46391c0c81909fa484446732b6a3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8771b25c819080da247bc3164cd9 completed March 20, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf77ac8e3c8190a846955a9eb65905 completed March 22, 2026, 5:01 a.m.
Created at: March 20, 2026, 2:04 p.m.