Triple

T6887102
Position Surface form Disambiguated ID Type / Status
Subject Marjorie Main E158948 entity
Predicate notableWork P4 FINISHED
Object Summer Stock E21245 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: Summer Stock | Statement: [Marjorie Main, notableWork, Summer Stock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Summer Stock
Context triple: [Marjorie Main, notableWork, Summer Stock]
  • A. Summer Stock chosen
    Summer Stock is a 1950 MGM musical film starring Judy Garland and Gene Kelly, known for its classic song-and-dance numbers and Garland’s iconic performance of “Get Happy.”
  • B. Summer Catch
    Summer Catch is a 2001 romantic comedy film about a young baseball player’s summer in the Cape Cod League, starring Freddie Prinze Jr. and Jessica Biel.
  • C. Summer Soft
    "Summer Soft" is a soulful, jazz-inflected ballad by Stevie Wonder, featured on his acclaimed 1976 album Songs in the Key of Life.
  • D. Summer Lent
    Summer Lent is a period of fasting and spiritual preparation in the Eastern Orthodox Church leading up to the Feast of the Dormition of the Mother of God in mid-August.
  • E. Summer
    "Summer" is a 1917 novel by Edith Wharton that explores themes of sexuality, social class, and female autonomy in a small New England town.
  • 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_69c688342f6c8190ad7eea6ba262db99 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d90e92488190b738676342ac6393 completed March 27, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c742e249508190ac95be97c0409d4a completed March 28, 2026, 2:54 a.m.
Created at: March 27, 2026, 2:23 p.m.