Triple

T15710269
Position Surface form Disambiguated ID Type / Status
Subject Cassian Elwes E380818 entity
Predicate notableWork P4 FINISHED
Object The Ledge E851003 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: The Ledge | Statement: [Cassian Elwes, notableWork, The Ledge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Ledge
Context triple: [Cassian Elwes, notableWork, The Ledge]
  • A. The Ledge chosen
    The Ledge is a psychological thriller film centered on a deadly moral dilemma between two men on a high-rise building ledge.
  • B. The Ledge
    The Ledge is a retail and dining area within Shangri-La Plaza, offering a mix of shops, restaurants, and lifestyle establishments.
  • C. The Ledge
    The Ledge is a suspenseful horror short story by Stephen King about a deadly bet that forces a man to inch his way around a narrow building ledge high above the ground.
  • D. Meet on the Ledge
    "Meet on the Ledge" is a classic folk-rock song by Fairport Convention, widely regarded as one of their signature anthems and a staple of British folk music.
  • E. Giant Ledge
    Giant Ledge is a popular series of dramatic cliff-top viewpoints in New York’s Catskill Mountains, known for panoramic vistas of the surrounding peaks and valleys.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8d8b648190842c635f2ae7bfa4 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757d74b481909c8332a09ae36b4f completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:45 a.m.