Triple

T2246238
Position Surface form Disambiguated ID Type / Status
Subject Gary "Eggsy" Unwin E49510 entity
Predicate familyName P18 FINISHED
Object Unwin
Unwin is the surname of Gary "Eggsy" Unwin, the working-class protagonist of the Kingsman film series.
 E246842 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: Unwin | Statement: [Gary "Eggsy" Unwin, familyName, Unwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Unwin
Context triple: [Gary "Eggsy" Unwin, familyName, Unwin]
  • A. The Whitworth
    The Whitworth is a prominent art gallery and museum in Manchester, England, renowned for its collections of fine art, textiles, and wallpapers and its integration with the surrounding park.
  • B. Morris
    Morris is the given first name of Moe Berg, the American Major League Baseball catcher who later became a World War II intelligence officer.
  • C. Swinton
    Swinton is a town in the City of Salford, Greater Manchester, England, known historically for its role in the coal mining and textile industries.
  • D. Haynrode
    Haynrode is a small village in the German state of Thuringia.
  • E. Norris
    Norris is a surname most notably associated with influential American politician George W. Norris, a progressive-era U.S. senator from Nebraska.
  • 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: Unwin
Triple: [Gary "Eggsy" Unwin, familyName, Unwin]
Generated description
Unwin is the surname of Gary "Eggsy" Unwin, the working-class protagonist of the Kingsman film series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Unwin
Target entity description: Unwin is the surname of Gary "Eggsy" Unwin, the working-class protagonist of the Kingsman film series.
  • A. The Whitworth
    The Whitworth is a prominent art gallery and museum in Manchester, England, renowned for its collections of fine art, textiles, and wallpapers and its integration with the surrounding park.
  • B. Morris
    Morris is the given first name of Moe Berg, the American Major League Baseball catcher who later became a World War II intelligence officer.
  • C. Swinton
    Swinton is a town in the City of Salford, Greater Manchester, England, known historically for its role in the coal mining and textile industries.
  • D. Haynrode
    Haynrode is a small village in the German state of Thuringia.
  • E. Norris
    Norris is a surname most notably associated with influential American politician George W. Norris, a progressive-era U.S. senator from Nebraska.
  • 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_69a88aa979788190ad6500f1d8eee2fc completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0ea75d881909d4e176a432f32e8 completed March 7, 2026, 6:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b147b388190a20a604cc176191f completed March 9, 2026, 6:39 a.m.
NEDg Description generation batch_69ae6b9edb688190a4e6e4a4ddf964f3 completed March 9, 2026, 6:41 a.m.
NED2 Entity disambiguation (via description) batch_69ae6bfbb6cc81909d647b3875450b4b completed March 9, 2026, 6:43 a.m.
Created at: March 4, 2026, 7:47 p.m.