Triple

T9039353
Position Surface form Disambiguated ID Type / Status
Subject Two Faces E216580 entity
Predicate title P38 FINISHED
Object Two Faces E216580 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: Two Faces | Statement: [Two Faces, title, Two Faces]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Two Faces
Context triple: [Two Faces, title, Two Faces]
  • A. Two Faces chosen
    Two Faces is a song by Bruce Springsteen from his 1987 album "Tunnel of Love," reflecting themes of inner conflict and emotional duality.
  • B. The Mirror Has Two Faces
    The Mirror Has Two Faces is a 1996 romantic comedy-drama film directed by and starring Barbra Streisand, featuring Lauren Bacall in an acclaimed supporting role.
  • C. Broken Face
    "Broken Face" is a raw, punk-influenced track by the Pixies, featured on their influential 1988 album *Surfer Rosa*.
  • D. Five Hundred Faces
    Five Hundred Faces is a song featured on the album "Harrow Songs."
  • E. About Face
    "About Face" is a 1952 American military comedy film starring William Tracy, known for its lighthearted portrayal of army 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_69ca83d22d488190adbce5e020e9cd1d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6ac46f4881909882403bb81db152 completed April 1, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfeb98e6008190a73c76c50aa7ed23 completed April 3, 2026, 4:32 p.m.
Created at: March 30, 2026, 7:09 p.m.