Triple

T19040600
Position Surface form Disambiguated ID Type / Status
Subject Rochelle Pingree E465989 entity
Predicate givenName P17 FINISHED
Object Rochelle 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: Rochelle | Statement: [Rochelle Pingree, givenName, Rochelle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rochelle
Context triple: [Rochelle Pingree, givenName, Rochelle]
  • A. Rochelle chosen
    Rochelle is the full given name of Chellie Pingree, an American politician serving as a U.S. Representative from Maine.
  • B. Rochelle
    Rochelle is the tough, outspoken, and fiercely protective mother of Chris in the sitcom "Everybody Hates Chris," known for her strict parenting and sharp humor.
  • C. Laurel
    Laurel is a feminine given name of English origin, derived from the laurel tree traditionally associated with honor and victory.
  • D. Laurel
    Laurel is a small city in Maryland known for its suburban character and location between Washington, D.C. and Baltimore.
  • E. Laurel
    Laurel is a small city in southern Montana, known as a residential and industrial community near Billings and a gateway to outdoor recreation in the Yellowstone region.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d80054c88190a9d3a49aed504235 completed April 20, 2026, 7:38 a.m.
Created at: April 10, 2026, 12:02 p.m.