Triple

T16842013
Position Surface form Disambiguated ID Type / Status
Subject Steve Punt E409435 entity
Predicate notableWork P4 FINISHED
Object Punt and Dennis
Punt and Dennis is a British comedy double act featuring Steve Punt and Hugh Dennis, known for their sketch and stand-up performances on television and radio.
 E1237045 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: Punt and Dennis | Statement: [Steve Punt, notableWork, Punt and Dennis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Punt and Dennis
Context triple: [Steve Punt, notableWork, Punt and Dennis]
  • A. Pete and Dud
    Pete and Dud were a celebrated British comedy double act consisting of Peter Cook and Dudley Moore, known for their surreal, satirical sketches in the 1960s.
  • B. Dennis
    Dennis is a character from Stephen King’s fantasy novel "The Eyes of the Dragon," known for his loyalty and involvement in the royal court’s intrigue.
  • C. Dennis
    Dennis is a character associated with Brewis, likely appearing as an ally in the same fictional or narrative context.
  • D. Dennis
    Dennis is a masculine given name of Greek origin, commonly used in English-speaking countries.
  • E. Dennis
    Dennis is a person or character notably linked to the concept or theme of pests, such as through pest control, infestation, or nuisance-related contexts.
  • 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: Punt and Dennis
Triple: [Steve Punt, notableWork, Punt and Dennis]
Generated description
Punt and Dennis is a British comedy double act featuring Steve Punt and Hugh Dennis, known for their sketch and stand-up performances on television and radio.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Punt and Dennis
Target entity description: Punt and Dennis is a British comedy double act featuring Steve Punt and Hugh Dennis, known for their sketch and stand-up performances on television and radio.
  • A. Pete and Dud
    Pete and Dud were a celebrated British comedy double act consisting of Peter Cook and Dudley Moore, known for their surreal, satirical sketches in the 1960s.
  • B. Dennis
    Dennis is the name of a notably destructive Atlantic hurricane whose impact led to its retirement from future storm name lists.
  • C. Dennis
    Dennis is a character from Stephen King’s fantasy novel "The Eyes of the Dragon," known for his loyalty and involvement in the royal court’s intrigue.
  • D. Dennis
    Dennis is a person or character notably linked to the concept or theme of pests, such as through pest control, infestation, or nuisance-related contexts.
  • E. Dennis
    Dennis is a character associated with Brewis, likely appearing as an ally in the same fictional or narrative context.
  • 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b35167a48190b45a459023e3ab1b completed April 18, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb199168819080a9ddc7534f19a7 completed May 10, 2026, 5:06 p.m.
NEDg Description generation batch_6a00bc22dc1c81909edc5cdb239f0ea8 completed May 10, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_6a00bce879648190acbd5645cd1a4ec8 completed May 10, 2026, 5:14 p.m.
Created at: April 10, 2026, 5:24 a.m.