Triple

T21090864
Position Surface form Disambiguated ID Type / Status
Subject Someone Like You E519632 entity
Predicate hasStory P11859 FINISHED
Object Poison 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: Poison | Statement: [Someone Like You, hasStory, Poison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poison
Context triple: [Someone Like You, hasStory, Poison]
  • A. Poison chosen
    "Poison" is a hit glam metal song by American band Poison, best known for its catchy hooks and prominent place in late-1980s rock.
  • B. Poison
    "Poison" is a high-energy electronic dance track by British rave group The Prodigy, known for its heavy breakbeats and gritty, experimental sound.
  • C. Poison
    Poison is a 2018 hip hop album by producer Swizz Beatz featuring a range of high-profile guest artists and a dark, hard-hitting sound.
  • D. Poison
    "Poison" is a 1991 independent drama film by Todd Haynes, noted for its experimental narrative structure and its role as a landmark work in the New Queer Cinema movement.
  • E. Poison
    Poison is a 2000s-era American Christian metalcore band known for its heavy sound and faith-based lyrics.
  • 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_69e0b507dd9081908fb8bfcbef4c8b46 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7094ea7f881909db83bf6961b41ec completed April 21, 2026, 5:21 a.m.
Created at: April 16, 2026, 2:51 p.m.