Triple

T2391270
Position Surface form Disambiguated ID Type / Status
Subject Maurice Ewing E48947 entity
Predicate notableStudent P4838 FINISHED
Object Walter Pitman E289609 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: Walter Pitman | Statement: [Maurice Ewing, notableStudent, Walter Pitman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walter Pitman
Context triple: [Maurice Ewing, notableStudent, Walter Pitman]
  • A. Walter Pitman chosen
    Walter Pitman was an American geophysicist and oceanographer known for his pioneering work on seafloor spreading and plate tectonics.
  • B. Walter Brewster
    Walter Brewster was a prominent local landowner and early settler after whom the Village of Brewster in New York was named.
  • C. William Nigh
    William Nigh was an American film director, screenwriter, and actor active from the silent era through the 1940s, known for his work on low-budget genre films.
  • D. Frank Pembleton
    Frank Pembleton is a brilliant, intense, and morally driven homicide detective from the television series "Homicide: Life on the Street."
  • E. Walter Frye
    Walter Frye was a 15th-century English composer known for his influential sacred vocal music, particularly masses and motets, during the early Renaissance.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc87457388190822d5506327db8f2 completed March 7, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69c6cad46d4081908f685d961d100d42 completed March 27, 2026, 6:22 p.m.
Created at: March 4, 2026, 7:57 p.m.