Triple

T22190591
Position Surface form Disambiguated ID Type / Status
Subject Sarah DuBois E548410 entity
Predicate familyName P18 FINISHED
Object DuBois E477660 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: DuBois | Statement: [Sarah DuBois, familyName, DuBois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DuBois
Context triple: [Sarah DuBois, familyName, DuBois]
  • A. DuBois
    DuBois is a small city in western Pennsylvania known historically for its coal and lumber industries and its role as a regional commercial center.
  • B. Ibram
    Ibram is the given name of Ibram X. Kendi, a prominent American historian and leading scholar of antiracism.
  • C. Dubois chosen
    Dubois is a common French-origin surname borne by numerous notable individuals across politics, arts, sciences, and sports.
  • D. Blackmon
    Blackmon is a surname most prominently associated with Larry Blackmon, the lead singer and founder of the funk band Cameo.
  • E. William Dubois
    William Dubois was the individual after whom Camp Dubois—associated with the Lewis and Clark Expedition—was named, likely a figure of local or historical significance in that context.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12ae3e8148190a23decd2dfe24e28 completed April 28, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0aae612f0c8190b10584b8d2e70d06 completed May 18, 2026, 6:14 a.m.
Created at: April 16, 2026, 8:35 p.m.