Triple

T20472349
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth March E502223 entity
Predicate childOf P120 FINISHED
Object Robert March 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: Robert March | Statement: [Elizabeth March, childOf, Robert March]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert March
Context triple: [Elizabeth March, childOf, Robert March]
  • A. Robert March chosen
    Robert March is a fictional character from Louisa May Alcott’s novel "Little Women," known as the gentle, principled father of the March sisters.
  • B. John March
    John March was a colonial military officer from New England who led the unsuccessful British provincial expedition against the French stronghold of Port Royal in 1707 during Queen Anne’s War.
  • C. William March
    William March was an American author best known for his 1954 psychological horror novel "The Bad Seed," which became a classic of the genre and inspired multiple adaptations.
  • D. Richard May
    Richard May is a music producer known for his work on the track "Bojangles."
  • E. James Gardner March
    James Gardner March was an influential American organizational theorist and political scientist known for his work on decision-making, organizational behavior, and the "garbage can" model of organizational choice.
  • 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6996197908190b6570e2a7fd6cf67 completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.