Triple

T10104208
Position Surface form Disambiguated ID Type / Status
Subject Carey Mulligan E216276 entity
Predicate notableWork P4 FINISHED
Object Skylight E374385 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: Skylight | Statement: [Carey Mulligan, notableWork, Skylight]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skylight
Context triple: [Carey Mulligan, notableWork, Skylight]
  • A. Skylight
    Skylight is a prominent Adirondack High Peak in New York’s High Peaks Wilderness, known for its open, rocky summit and expansive panoramic views.
  • B. Skylight chosen
    "Skylight" is a critically acclaimed stage play by David Hare that explores the complex emotional and social tensions between former lovers reunited after years apart.
  • C. Sky Light
    Sky Light is an abstract painting by American artist Alma Thomas, characterized by her signature mosaic-like blocks of color evoking light and atmospheric movement.
  • D. Moonglow
    "Moonglow" is a classic jazz standard from the 1930s that became widely popular through swing-era recordings and remains a frequently performed tune in the jazz repertoire.
  • E. October Light
    October Light is a 1976 novel by American author John Gardner that explores themes of aging, family conflict, and political ideology in rural Vermont.
  • 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_69ca83d039f08190b9d10363221c69fb completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd09c961081909848acec4438c300 completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b6dcca848190851f6f1968fe244c completed April 5, 2026, 7:24 p.m.
Created at: March 30, 2026, 9:03 p.m.