Triple

T11522257
Position Surface form Disambiguated ID Type / Status
Subject Edith Atwater E273193 entity
Predicate spouse P13 FINISHED
Object Hugh Marlowe E21702 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: Hugh Marlowe | Statement: [Edith Atwater, spouse, Hugh Marlowe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Marlowe
Context triple: [Edith Atwater, spouse, Hugh Marlowe]
  • A. Hugh Marlowe chosen
    Hugh Marlowe was an American film, television, and stage actor best known for his roles in classic mid-20th-century movies and popular TV series.
  • B. Christopher Marlowe
    Christopher Marlowe was a pioneering Elizabethan playwright and poet whose works, including "Doctor Faustus" and "Tamburlaine," helped shape the development of English Renaissance drama.
  • C. Marlowe
    Marlowe is a neo-noir crime thriller film centered on the iconic private detective Philip Marlowe, adapted from John Banville’s novel "The Black-Eyed Blonde."
  • D. Francis Kyd
    Francis Kyd was the father of the Elizabethan dramatist Thomas Kyd, likely a London-based scrivener or tradesman in the late 16th century.
  • E. Thomas Kyd
    Thomas Kyd was a pioneering English Renaissance dramatist best known for his highly influential revenge tragedy "The Spanish Tragedy."
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fd129c88190893b95222480e04a completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e62551a36081908ef6418fe8e2155c completed April 20, 2026, 1:08 p.m.
Created at: April 8, 2026, 9:37 p.m.