Triple

T15368396
Position Surface form Disambiguated ID Type / Status
Subject In Your Eyes E367474 entity
Predicate castMember P1668 FINISHED
Object Mark Feuerstein E1012703 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: Mark Feuerstein | Statement: [In Your Eyes, castMember, Mark Feuerstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Feuerstein
Context triple: [In Your Eyes, castMember, Mark Feuerstein]
  • A. Mark Feuerstein chosen
    Mark Feuerstein is an American actor best known for his lead role as Dr. Hank Lawson on the television series "Royal Pains."
  • B. Steven Fierberg
    Steven Fierberg is an American cinematographer known for his work on feature films and television series, including the romantic drama "Love & Other Drugs."
  • C. Stephen Endlicher
    Stephen Endlicher was a 19th-century Austrian botanist and linguist known for his influential work in plant taxonomy and classification.
  • D. Robert Weinbach
    Robert Weinbach is a film producer known for his work on independent genre movies, including the 2012 horror film "Shiver."
  • E. Allan Arkush
    Allan Arkush is an American film and television director and producer best known for cult classic rock comedies like "Rock 'n' Roll High School" and his extensive work on episodic TV dramas.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e4a7cdc8190b7b48c97e774c306 completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff364d82c48190b116528b5c00e918 completed May 9, 2026, 1:27 p.m.
Created at: April 10, 2026, 3:18 a.m.