Triple

T15451521
Position Surface form Disambiguated ID Type / Status
Subject Lyndon Dykes E371661 entity
Predicate familyName P18 FINISHED
Object Dykes E797542 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: Dykes | Statement: [Lyndon Dykes, familyName, Dykes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dykes
Context triple: [Lyndon Dykes, familyName, Dykes]
  • A. Dykes chosen
    Dykes is a surname most notably associated with American football coach Spike Dykes and his family.
  • B. Dykes to Watch Out For
    Dykes to Watch Out For is a long-running, influential comic strip by Alison Bechdel that chronicles the lives and politics of a diverse group of lesbian friends.
  • C. The Brecks
    The Brecks is a distinctive region in eastern England characterized by its sandy soils, heathland landscapes, and unique biodiversity.
  • D. Errançities
    Errançities is a poetry collection by Quincy Troupe that explores themes of movement, identity, and African diasporic experience through innovative, jazz-inflected language.
  • E. The Ponds
    The Ponds is a residential neighborhood within the planned community of Burke Centre in Fairfax County, Virginia.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03efaf82c81908b464e37ce9c159a completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff21b1e9688190a283dbc552072ce0 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:30 a.m.