Triple

T16904875
Position Surface form Disambiguated ID Type / Status
Subject Thomas Marshall E424534 entity
Predicate parentOf P120 FINISHED
Object Mary Marshall E424534 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: Mary Marshall | Statement: [Thomas Marshall, parentOf, Mary Marshall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Marshall
Context triple: [Thomas Marshall, parentOf, Mary Marshall]
  • A. Mary Marshall chosen
    Mary Marshall is known primarily as the daughter of Thomas Marshall, a figure of historical and familial significance.
  • B. Margaret Pope
    Margaret Pope is a New Zealand public servant and political adviser best known for her long-term partnership with former Prime Minister David Lange.
  • C. Anne Walmesley
    Anne Walmesley was an English gentlewoman of the 17th century best known as the mother of Thomas Osborne, 1st Duke of Leeds, a prominent statesman under Charles II and William III.
  • D. Emily Rutherfurd
    Emily Rutherfurd is an American actress best known for her comedic television roles, including a prominent part on the sitcom "The New Adventures of Old Christine."
  • E. Margaret Jasper
    Margaret Jasper was the wife of English naval officer Sir William Penn and the mother of William Penn, the founder of Pennsylvania.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8df454c8190898ebdd75985e51c completed April 18, 2026, 6:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7b7b698819081d2e39976b69587 completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:30 a.m.