Triple

T3086459
Position Surface form Disambiguated ID Type / Status
Subject Ant-Man E64383 entity
Predicate alterEgo P39 FINISHED
Object Scott Lang E234637 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: Scott Lang | Statement: [Ant-Man, alterEgo, Scott Lang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scott Lang
Context triple: [Ant-Man, alterEgo, Scott Lang]
  • A. Scott Lang chosen
    Scott Lang is the Marvel Cinematic Universe's Ant-Man, a former thief turned size-shifting superhero known for his humor, ingenuity, and role in the Avengers' battles.
  • B. Hawkeye
    Hawkeye is a Marvel Cinematic Universe Disney+ series centered on the archer superhero Clint Barton and his protégé Kate Bishop.
  • C. Philip Holland
    Philip Holland was an 18th-century English Presbyterian minister and educator known for his influential teaching and theological work associated with Warrington Academy.
  • D. Alexander Pierce (MCU)
    Alexander Pierce (MCU) is a high-ranking S.H.I.E.L.D. official secretly serving as a key Hydra mastermind and primary antagonist in "Captain America: The Winter Soldier."
  • E. Hank Pym
    Hank Pym is a Marvel Comics scientist and superhero best known as the original Ant-Man and the creator of the size-changing Pym Particles and Ultron.
  • 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_69ad857bb4c88190a4cf27893fcabed8 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1ec187c819084565514ebb99cdb completed March 8, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f89e6f5c8190993794e2c9977ee6 completed March 11, 2026, 11:19 p.m.
Created at: March 8, 2026, 3:03 p.m.