Triple

T18785367
Position Surface form Disambiguated ID Type / Status
Subject What On Earth E459359 entity
Predicate name P16 FINISHED
Object What On Earth 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: What On Earth | Statement: [What On Earth, name, What On Earth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: What On Earth
Context triple: [What On Earth, name, What On Earth]
  • A. What On Earth chosen
    What On Earth is a natural history and science exhibition at Weston Park Museum that explores the wonders of the natural world through interactive displays and collections.
  • B. Here on Earth
    "Here on Earth" is a country song by American singer Tim McGraw, featured as the title track of his 2020 studio album.
  • C. Day on Earth
    "Day on Earth" is a modern dance work by pioneering American choreographer Doris Humphrey that explores themes of human experience and the cycle of life.
  • D. Earth-Numb
    Earth-Numb is a poem by Ted Hughes included in his collection *Moortown Diary*, reflecting his characteristic intense engagement with nature and rural life.
  • E. The Day It Came to Earth
    The Day It Came to Earth is a 1977 low-budget sci-fi comedy film about a group of college students who encounter an alien after a meteor crashes near their favorite hangout.
  • 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_69d8d396f54c8190ba49db31e8743842 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5978154ac819096356d2a488b45f0 completed April 20, 2026, 3:03 a.m.
Created at: April 10, 2026, 11:52 a.m.