Triple

T16636307
Position Surface form Disambiguated ID Type / Status
Subject AGBO E404212 entity
Predicate produced P490 FINISHED
Object Relic E893809 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: Relic | Statement: [AGBO, produced, Relic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Relic
Context triple: [AGBO, produced, Relic]
  • A. Relic
    Relic is a fashion accessories brand under Fossil Group known for its affordable, casual watches, handbags, and small leather goods.
  • B. Relic chosen
    Relic is a 2020 Australian psychological horror film that explores themes of dementia and generational trauma through a haunting, slow-burn narrative.
  • C. Relic Hunter
    Relic Hunter is a Canadian fantasy–adventure television series that follows a globe-trotting archaeologist as she tracks down ancient artifacts, blending action, mystery, and historical intrigue.
  • D. Relics
    "Relics" is a Star Trek: The Next Generation episode best known for featuring the return of original series engineer Montgomery "Scotty" Scott after decades trapped in a transporter buffer.
  • E. The Relic
    The Relic is a 1997 science fiction horror film about a monstrous creature stalking a Chicago museum, based on the novel by Douglas Preston and Lincoln Child.
  • 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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378ea4b848190bf7c95dad8a855f0 completed April 18, 2026, 12:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a007dc28df48190b01c1328df24df60 completed May 10, 2026, 12:44 p.m.
Created at: April 10, 2026, 5:17 a.m.