Triple

T2832653
Position Surface form Disambiguated ID Type / Status
Subject Carl Weathers E62274 entity
Predicate characterRole P268 FINISHED
Object Dillon
Dillon is a tough, muscular CIA operative portrayed by Carl Weathers in the 1987 sci-fi action film "Predator."
 E303411 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: Dillon | Statement: [Carl Weathers, characterRole, Dillon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dillon
Context triple: [Carl Weathers, characterRole, Dillon]
  • A. Dixon
    Dixon is a small agricultural city in Northern California known historically for sheep ranching and its annual May Fair.
  • B. Dawson
    Dawson is a common English-language surname of Anglo-Saxon origin, meaning "son of David."
  • C. Dedridge
    Dedridge is a residential neighbourhood within the new town of Livingston in West Lothian, Scotland.
  • D. Leland
    Leland is a masculine given name of English origin, historically associated with figures such as American industrialist and Stanford University founder Leland Stanford.
  • E. Jennings
    Jennings is a common English surname borne by numerous notable individuals across fields such as music, sports, politics, and entertainment.
  • 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: Dillon
Triple: [Carl Weathers, characterRole, Dillon]
Generated description
Dillon is a tough, muscular CIA operative portrayed by Carl Weathers in the 1987 sci-fi action film "Predator."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dillon
Target entity description: Dillon is a tough, muscular CIA operative portrayed by Carl Weathers in the 1987 sci-fi action film "Predator."
  • A. Dixon
    Dixon is a small agricultural city in Northern California known historically for sheep ranching and its annual May Fair.
  • B. Dawson
    Dawson is a common English-language surname of Anglo-Saxon origin, meaning "son of David."
  • C. Dedridge
    Dedridge is a residential neighbourhood within the new town of Livingston in West Lothian, Scotland.
  • D. Leland
    Leland is a masculine given name of English origin, historically associated with figures such as American industrialist and Stanford University founder Leland Stanford.
  • E. Jennings
    Jennings is a common English surname borne by numerous notable individuals across fields such as music, sports, politics, and entertainment.
  • 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_69ab4c3c39188190955b9c49d98463d8 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdebe95188190bf65fb4cd88e2ec5 completed March 7, 2026, 8:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69afe8bb92b08190b1de7e6973d96301 completed March 10, 2026, 9:47 a.m.
NEDg Description generation batch_69afea972cc8819087455f3233f84d21 completed March 10, 2026, 9:55 a.m.
NED2 Entity disambiguation (via description) batch_69b003cb1b2081909ddf2e6bae3e5491 completed March 10, 2026, 11:43 a.m.
Created at: March 6, 2026, 10:01 p.m.