Triple

T1791929
Position Surface form Disambiguated ID Type / Status
Subject Viewliner sleeping cars E39514 entity
Predicate usedOn P2367 FINISHED
Object Crescent E9916 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: Crescent | Statement: [Viewliner sleeping cars, usedOn, Crescent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crescent
Context triple: [Viewliner sleeping cars, usedOn, Crescent]
  • A. Crescent chosen
    Crescent is a long-distance Amtrak passenger train that runs between New York City and New Orleans, serving major cities along the U.S. East Coast and Deep South.
  • B. The Crescent
    The Crescent is an iconic Georgian crescent-shaped building in Buxton, Derbyshire, historically developed as a grand spa hotel and assembly rooms and now a prominent architectural landmark.
  • C. Arida
    Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
  • D. Halfmoon
    Halfmoon is a suburban town in eastern New York State known for its residential communities and proximity to the Capital District.
  • E. Ishbak
    Ishbak is a lesser-known son of the biblical patriarch Abraham, mentioned among the children he had later in life.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa65392b2c81909bf4d619bd347f54 completed March 6, 2026, 5:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69adbf54330c81908046b519a0297760 completed March 8, 2026, 6:26 p.m.
Created at: March 4, 2026, 7:32 p.m.