Triple

T9738891
Position Surface form Disambiguated ID Type / Status
Subject Captain America: The Winter Soldier E236134 entity
Predicate featuresCharacter P626 FINISHED
Object Falcon E202138 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: Falcon | Statement: [Captain America: The Winter Soldier, featuresCharacter, Falcon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Falcon
Context triple: [Captain America: The Winter Soldier, featuresCharacter, Falcon]
  • A. Falcon
    The Falcon is a bird of prey known for its exceptional speed, keen vision, and use in the sport of falconry.
  • B. Falcon chosen
    Falcon is a Marvel Comics superhero and member of the Avengers, known for his advanced winged flight suit and partnership with Captain America.
  • C. Falcon
    Falcon is a family of large language models designed for high-performance text generation and widely used in open-source AI applications.
  • D. Fighting Falcon
    Fighting Falcon is the nickname of the F-16, a widely used American multirole fighter aircraft known for its agility and versatility in combat.
  • E. Taita falcon
    The Taita falcon is a small, rare African bird of prey known for its fast, agile flight and preference for nesting on cliffs in rugged, remote landscapes.
  • 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_69ca84d313e88190983ee6ffd0ef60d2 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9ef43fec8190987628f401a27436 completed April 1, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1afe0dab48190832ab77265c09d70 completed April 5, 2026, 12:42 a.m.
Created at: March 30, 2026, 8:22 p.m.