Triple

T20828032
Position Surface form Disambiguated ID Type / Status
Subject The Fantastic Four #5 E512755 entity
Predicate featuresCharacter P626 FINISHED
Object Human Torch 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: Human Torch | Statement: [The Fantastic Four #5, featuresCharacter, Human Torch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Human Torch
Context triple: [The Fantastic Four #5, featuresCharacter, Human Torch]
  • A. Human Torch chosen
    Human Torch is a Marvel Comics superhero, most commonly known as the fiery, flight-capable member of the Fantastic Four who can engulf his body in flames and control fire.
  • B. Human Torch
    Human Torch is a Golden Age Marvel Comics android superhero who can engulf his body in flames and fly.
  • C. Torches
    "Torches" is a song by the band Revolutions per Minute, likely featuring their characteristic energetic rock sound and socially charged themes.
  • D. Torch
    "Torch" is a 2002 synth-pop album by British duo Soft Cell, known for its dark electronic sound and introspective lyrics.
  • E. Torch
    Torch is an American rapper best known as a member of Rick Ross’s Maybach Music Group collective.
  • 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_69e0b4ce39108190a6e8e5df4f1c8dc5 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c31e387481909fcf323f97019803 completed April 21, 2026, 12:21 a.m.
Created at: April 16, 2026, 12:42 p.m.