Triple

T23488000
Position Surface form Disambiguated ID Type / Status
Subject Casper Crump E570591 entity
Predicate appearedIn P795 FINISHED
Object Arrow 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: Arrow | Statement: [Casper Crump, appearedIn, Arrow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arrow
Context triple: [Casper Crump, appearedIn, Arrow]
  • A. Arrow
    Arrow is the nickname of the Avro Canada CF-105 Arrow, a Canadian supersonic interceptor aircraft developed in the 1950s.
  • B. Arrow
    Arrow is the English translation of "Freccia," the nickname of the Italian World War II fighter aircraft Fiat G.50.
  • C. Arrow chosen
    Arrow is a popular American superhero television series based on the DC Comics character Green Arrow, known for launching the interconnected "Arrowverse" franchise.
  • D. Arrow
    Arrow is a common English surname borne by various individuals, including the influential economist Kenneth Arrow.
  • E. Arrow
    Arrow is a regional passenger rail service brand used for trains operating between San Bernardino and Redlands in Southern California.
  • 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7d9cc08819084c532b069f867ee completed April 29, 2026, 6:40 a.m.
Created at: April 17, 2026, 6:04 p.m.