Triple

T17781563
Position Surface form Disambiguated ID Type / Status
Subject May Andersen E443911 entity
Predicate name P16 FINISHED
Object May Andersen NE NERFINISHED

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: May Andersen | Statement: [May Andersen, name, May Andersen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: May Andersen
Context triple: [May Andersen, name, May Andersen]
  • A. May Andersen chosen
    May Andersen is a Danish model and former Victoria's Secret runway regular known for her work in high-fashion campaigns and magazines.
  • B. Malvina Poulsen
    Malvina Poulsen was the wife of English character actor H. B. Warner, known for his roles in early 20th-century stage and film productions.
  • C. Ottilia Marie Jacobsen
    Ottilia Marie Jacobsen was the wife of Danish brewer and art patron Carl Jacobsen, associated with the Carlsberg brewing dynasty and its cultural legacy.
  • D. Elsa Kast
    Elsa Kast is the central scientist protagonist in the science-fiction horror film "Splice," known for creating a dangerous human-animal hybrid.
  • E. Tulip Olsen
    Tulip Olsen is the introspective, puzzle-loving protagonist of the animated anthology series "Infinity Train," known for her emotional journey of self-discovery aboard a mysterious, ever-changing train.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ef17708190bdf7e2adbf14ddc2 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4872152508190870a1765e0972ec1 completed April 19, 2026, 7:41 a.m.
Created at: April 10, 2026, 10:12 a.m.