Triple

T16842002
Position Surface form Disambiguated ID Type / Status
Subject Steve Punt E409435 entity
Predicate familyName P18 FINISHED
Object Punt
Punt is a surname of English origin most notably associated with British comedian and writer Steve Punt.
 E1237044 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 | Statement: [Steve Punt, familyName, Punt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Punt
Context triple: [Steve Punt, familyName, Punt]
  • A. Punt
    Punt was an ancient trading region, likely located along the Red Sea or Horn of Africa, famed in Egyptian records for its exports of incense, ebony, gold, and exotic animals.
  • B. Puttu
    Puttu is a traditional South Indian steamed rice cake, typically cylindrical and layered with grated coconut, commonly eaten for breakfast in Kerala.
  • C. Pio
    Pio is the costumed mascot representing the athletic teams and school spirit of Lewis & Clark College.
  • D. Piglio
    Piglio is a historic hill town in Italy’s Lazio region, known for its medieval architecture and Cesanese del Piglio wine production.
  • E. Ponti
    Ponti is an Italian surname most famously associated with Gio Ponti, the influential 20th-century architect and designer.
  • 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
Triple: [Steve Punt, familyName, Punt]
Generated description
Punt is a surname of English origin most notably associated with British comedian and writer Steve Punt.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Punt
Target entity description: Punt is a surname of English origin most notably associated with British comedian and writer Steve Punt.
  • A. Punt
    Punt was an ancient trading region, likely located along the Red Sea or Horn of Africa, famed in Egyptian records for its exports of incense, ebony, gold, and exotic animals.
  • B. Puttu
    Puttu is a traditional South Indian steamed rice cake, typically cylindrical and layered with grated coconut, commonly eaten for breakfast in Kerala.
  • C. Pio
    Pio is the costumed mascot representing the athletic teams and school spirit of Lewis & Clark College.
  • D. Piglio
    Piglio is a historic hill town in Italy’s Lazio region, known for its medieval architecture and Cesanese del Piglio wine production.
  • E. Ponti
    Ponti is an Italian surname most famously associated with Gio Ponti, the influential 20th-century architect and designer.
  • 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.