Triple

T17749720
Position Surface form Disambiguated ID Type / Status
Subject Old Well E443079 entity
Predicate hasEnglishTitle P3437 FINISHED
Object Old Well NE NERFINISHED

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: Old Well | Statement: [Old Well, hasEnglishTitle, Old Well]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Well
Context triple: [Old Well, hasEnglishTitle, Old Well]
  • A. Old Well chosen
    Old Well is an iconic neoclassical rotunda and campus symbol of the University of North Carolina at Chapel Hill, traditionally associated with good luck for students who drink from it.
  • B. Old Well
    Old Well is a 1986 Chinese drama film directed by Wu Tianming and noted for its acclaimed cinematography by Zhang Yimou.
  • C. Mary’s Well
    Mary’s Well is a historic spring and pilgrimage site in Nazareth traditionally associated with the Virgin Mary and the Annunciation.
  • D. The Well
    "The Well" is a song by American singer-songwriter Smog (Bill Callahan), featured on his 2005 album *A River Ain't Too Much to Love*, known for its sparse, introspective folk style.
  • E. The Well
    The Well is a film featuring actress Dorothy Patrick, known for her roles in mid-20th-century American cinema.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48418c0188190beb31809b40e4648 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.