Triple

T11235007
Position Surface form Disambiguated ID Type / Status
Subject Random Harvest E265920 entity
Predicate starring P1507 FINISHED
Object Philip Dorn E754291 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: Philip Dorn | Statement: [Random Harvest, starring, Philip Dorn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip Dorn
Context triple: [Random Harvest, starring, Philip Dorn]
  • A. Philip Dorn chosen
    Philip Dorn was a Dutch-born actor known for his roles in Hollywood films of the 1940s, often portraying dignified European characters.
  • B. Ed Dorn
    Ed Dorn was an American poet associated with the Black Mountain school, known for his incisive, often politically charged verse and his long poem "Gunslinger."
  • C. Dan Morgenstern
    Dan Morgenstern is an American jazz historian, critic, and archivist renowned for his leadership of the Institute of Jazz Studies and his Grammy-winning liner notes.
  • D. David Burnside
    David Burnside is a Northern Irish public relations executive and former Ulster Unionist Party politician who served as a Member of Parliament for South Antrim.
  • E. Brian Beattie
    Brian Beattie is an American musician, producer, and arranger known for his inventive orchestral and studio work with indie and alternative artists.
  • 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_69d6aac656d48190b275efaa7d6074ee completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e903b8ec81909f9c89776d35c650 completed April 9, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4ad56013481909f931505824e3b42 completed April 19, 2026, 10:24 a.m.
Created at: April 8, 2026, 9:30 p.m.