Triple

T14520910
Position Surface form Disambiguated ID Type / Status
Subject Todd Haynes E340647 entity
Predicate notableWork P4 FINISHED
Object Carol E307551 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: Carol | Statement: [Todd Haynes, notableWork, Carol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol
Context triple: [Todd Haynes, notableWork, Carol]
  • A. Carol
    Carol is a feminine given name commonly used in English-speaking countries, often associated with figures in entertainment and literature.
  • B. Carol chosen
    Carol is a critically acclaimed 2015 romantic drama film, directed by Todd Haynes and starring Cate Blanchett and Rooney Mara, about a forbidden love affair between two women in 1950s New York.
  • C. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • D. Barbara
    Barbara is a station on Paris Métro Line 4 serving the southern suburbs of the French capital.
  • E. Nancy
    Nancy is a feminine given name of Hebrew origin meaning "grace" that became especially popular in English-speaking countries in the 20th century.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a4b71688190ae9ebccdc81d09f8 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.