Triple

T14767395
Position Surface form Disambiguated ID Type / Status
Subject Mickey O'Neil E347031 entity
Predicate hasNameInFiction P34792 FINISHED
Object Mickey
Mickey is a fast-talking, bare-knuckle boxing Irish Traveller character played by Brad Pitt in the 2000 crime film "Snatch."
E1119151 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: Mickey | Statement: [Mickey O'Neil, hasNameInFiction, Mickey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mickey
Context triple: [Mickey O'Neil, hasNameInFiction, Mickey]
  • A. Mickey
    Mickey is a character from the virtual reality co-op shooter game "After the Fall," set in a post-apocalyptic, frozen Los Angeles overrun by monstrous creatures.
  • B. Mickey
    Mickey is the nickname of English actress Mickey Sumner, known for her roles in film and television such as "Frances Ha" and "Snowpiercer."
  • C. Mickey
    Mickey is a common diminutive form of the given name Michael, often used as a familiar or informal first name.
  • D. Mickey
    Mickey is the central protagonist of the 1938 horse-racing drama film "Stablemates," around whom the story’s emotional and narrative arc revolves.
  • E. Mickey
    Mickey is the nickname of Mickey Rivers, a former Major League Baseball center fielder known for his speed and leadoff hitting, especially with the New York Yankees in the late 1970s.
  • 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: Mickey
Triple: [Mickey O'Neil, hasNameInFiction, Mickey]
Generated description
Mickey is a fast-talking, bare-knuckle boxing Irish Traveller character played by Brad Pitt in the 2000 crime film "Snatch."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mickey
Target entity description: Mickey is a fast-talking, bare-knuckle boxing Irish Traveller character played by Brad Pitt in the 2000 crime film "Snatch."
  • A. Mickey
    Mickey is the nickname of English actress Mickey Sumner, known for her roles in film and television such as "Frances Ha" and "Snowpiercer."
  • B. Mickey
    Mickey is the central protagonist of the 1938 horse-racing drama film "Stablemates," around whom the story’s emotional and narrative arc revolves.
  • C. Mickey
    Mickey is a member of the Orbital Drop Shock Troopers (ODST) squad in the Halo universe, known for his role as the squad’s demolitions expert in Halo 3: ODST.
  • D. Mickey
    Mickey is the nickname of Mickey Rivers, a former Major League Baseball center fielder known for his speed and leadoff hitting, especially with the New York Yankees in the late 1970s.
  • E. Mickey
    Mickey is the commonly used nickname of Mickey Leland, an American congressman and humanitarian known for his work on hunger and poverty issues.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec81236f081908063bb4350b7b985 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cf68d94819093567bc630f67b60 completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe1b0056988190b14560470428d895 completed May 8, 2026, 5:18 p.m.
NED2 Entity disambiguation (via description) batch_69fe1b97e8148190b23a555b9f2c7f1f completed May 8, 2026, 5:21 p.m.
Created at: April 10, 2026, 1:30 a.m.