Triple

T11898386
Position Surface form Disambiguated ID Type / Status
Subject Fleetwood Mac E283090 entity
Predicate notableWork P4 FINISHED
Object Tusk E389493 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: Tusk | Statement: [Fleetwood Mac, notableWork, Tusk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tusk
Context triple: [Fleetwood Mac, notableWork, Tusk]
  • A. Tusk
    Tusk is a Polish surname most prominently associated with Donald Tusk, a leading Polish and European Union politician.
  • B. Tusk
    Tusk is the live Russian boar mascot that represents the University of Arkansas Razorbacks football team at games and events.
  • C. Tusk chosen
    Tusk is a 2014 horror-comedy film written and directed by Kevin Smith about a podcaster who is grotesquely transformed into a walrus by a deranged seafarer.
  • D. Komo
    The Komo are an ethnic group indigenous to western Ethiopia, particularly associated with the Gambela Region, with their own distinct language and cultural traditions.
  • E. Tig
    Tig is a deity in Germanic mythology cognate with the Norse god Týr, associated with war, law, and heroic honor.
  • 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8dd13cc10819089d8d5103e562924 completed April 10, 2026, 11:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f418205b788190a4b1b81d89cf7fff completed May 1, 2026, 3:04 a.m.
Created at: April 8, 2026, 9:44 p.m.