Triple

T12231727
Position Surface form Disambiguated ID Type / Status
Subject Luke Cage E291490 entity
Predicate enemy P4567 FINISHED
Object Cottonmouth
Cottonmouth is a crime boss and drug kingpin in Marvel's Luke Cage series, known for his ruthless control of Harlem and frequent clashes with the hero.
 E969260 NE FINISHED

How this triple was built (4 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: Cottonmouth | Statement: [Luke Cage, enemy, Cottonmouth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cottonmouth
Context triple: [Luke Cage, enemy, Cottonmouth]
  • A. Víbora
    Víbora is a traditional residential neighborhood in Havana, Cuba, known for its dense urban fabric and local commercial activity.
  • B. Copperheads
    Copperheads were a faction of Northern Democrats during the American Civil War who opposed the war and advocated for a negotiated peace with the Confederacy.
  • C. Kobra
    Kobra is a spinning disk roller coaster attraction at Chessington World of Adventures in the UK.
  • D. Constrictor
    Constrictor is a water slide attraction at Wet'n'Wild Gold Coast known for its tight twists and high-speed tube-style turns.
  • E. Mushmouth
    Mushmouth is a mumble-mouthed, beanie-wearing member of Fat Albert’s junkyard gang known for his comically garbled speech and good-natured personality.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cottonmouth
Triple: [Luke Cage, enemy, Cottonmouth]
Generated description
Cottonmouth is a crime boss and drug kingpin in Marvel's Luke Cage series, known for his ruthless control of Harlem and frequent clashes with the hero.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cottonmouth
Target entity description: Cottonmouth is a crime boss and drug kingpin in Marvel's Luke Cage series, known for his ruthless control of Harlem and frequent clashes with the hero.
  • A. Víbora
    Víbora is a traditional residential neighborhood in Havana, Cuba, known for its dense urban fabric and local commercial activity.
  • B. Copperheads
    Copperheads were a faction of Northern Democrats during the American Civil War who opposed the war and advocated for a negotiated peace with the Confederacy.
  • C. Kobra
    Kobra is a spinning disk roller coaster attraction at Chessington World of Adventures in the UK.
  • D. Constrictor
    Constrictor is a water slide attraction at Wet'n'Wild Gold Coast known for its tight twists and high-speed tube-style turns.
  • E. Mushmouth
    Mushmouth is a mumble-mouthed, beanie-wearing member of Fat Albert’s junkyard gang known for his comically garbled speech and good-natured personality.
  • F. None of above. chosen

Provenance (5 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ca45bd48190b8b7f6b29b6bb25b completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aad2d488190ba36588e3376ca1a completed May 2, 2026, 2:31 p.m.
NEDg Description generation batch_69f60bdca250819090b4b4cc84d343f4 completed May 2, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69f60cd1668881908f43d895fcfba0aa completed May 2, 2026, 2:40 p.m.
Created at: April 8, 2026, 9:51 p.m.