Triple

T6036017
Position Surface form Disambiguated ID Type / Status
Subject Frank Mill E134422 entity
Predicate givenName P17 FINISHED
Object Frank E324418 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: Frank | Statement: [Frank Mill, givenName, Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank
Context triple: [Frank Mill, givenName, Frank]
  • A. Frank
    Frank is a key supporting character in the post-apocalyptic horror film "28 Days Later," known as a protective father trying to keep his daughter safe amid a devastating viral outbreak in London.
  • B. Frank
    Frank is the Allied reporting name for the Japanese Nakajima Ki-84, a highly capable World War II fighter aircraft used by the Imperial Japanese Army Air Service.
  • C. Frank
    Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
  • D. Frank
    Frank is the given first name of the American contemporary street artist and graphic designer Shepard Fairey, known for his iconic "OBEY" and Barack Obama "Hope" posters.
  • E. Frank chosen
    Frank is the given name of British screenwriter and children's author Frank Cottrell-Boyce.
  • 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_69c00875db5c819099dd5bb833ec43c2 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056b4e3ec819089b2d119ea2953fe completed March 22, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1138cb2388190a80562a835388dc3 completed March 23, 2026, 10:18 a.m.
Created at: March 22, 2026, 4:08 p.m.