Triple

T15904339
Position Surface form Disambiguated ID Type / Status
Subject Michael Finnell E385670 entity
Predicate notableWork P4 FINISHED
Object Matinee E1046755 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: Matinee | Statement: [Michael Finnell, notableWork, Matinee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matinee
Context triple: [Michael Finnell, notableWork, Matinee]
  • A. Matinee chosen
    Matinee is a 1993 comedy film directed by Joe Dante that satirizes Cold War-era America through the story of a showman premiering a gimmicky horror movie during the Cuban Missile Crisis.
  • B. Mattinata
    Mattinata is a coastal town in Italy’s Apulia region, known for its white cliffs, pebble beaches, and scenic setting on the Gargano promontory.
  • C. Matinee Theatre
    Matinee Theatre was a 1950s American live anthology television series that presented a different dramatic play each weekday afternoon.
  • D. Living at the Movies
    Living at the Movies is a poetry collection by American writer and punk icon Jim Carroll, known for its vivid, streetwise depictions of urban life and youth.
  • E. Mélo
    Mélo is a 1986 French romantic drama film by director Alain Resnais, adapted from Henri Bernstein’s 1929 play and noted for its theatrical style and exploration of memory and passion.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1563f74d88190a3d92ca0ad46e867 completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe6e844481908227ec9e46ac9f4d completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:52 a.m.