Triple

T23036268
Position Surface form Disambiguated ID Type / Status
Subject Ham, Wiltshire E573602 entity
Predicate postTown P2711 FINISHED
Object Hungerford
Hungerford is a historic market town in Berkshire, England, known for its antique shops and location along the Kennet and Avon Canal.
 E42529 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: Hungerford | Statement: [Ham, Wiltshire, postTown, Hungerford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hungerford
Context triple: [Ham, Wiltshire, postTown, Hungerford]
  • A. Hungerford
    Hungerford is a historic market town and civil parish in West Berkshire, England, situated on the River Kennet and the Kennet and Avon Canal.
  • B. Hensel
    Hensel is a German surname most notably associated with mathematician Kurt Hensel, known for introducing p-adic numbers.
  • C. Hartung
    Hartung is a German surname borne by various notable individuals across fields such as art, sports, and politics.
  • D. Gamelin
    Gamelin is a French surname most notably associated with General Maurice Gamelin, the commander-in-chief of the French Army at the start of World War II.
  • E. Hilbert
    Hilbert is the male player character and primary protagonist from the Pokémon Black and White video games in the fifth generation of the Pokémon series.
  • 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: Hungerford
Triple: [Ham, Wiltshire, postTown, Hungerford]
Generated description
Hungerford is a historic market town in Berkshire, England, known for its antique shops and location along the Kennet and Avon Canal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hungerford
Target entity description: Hungerford is a historic market town in Berkshire, England, known for its antique shops and location along the Kennet and Avon Canal.
  • A. Hungerford chosen
    Hungerford is a historic market town and civil parish in West Berkshire, England, situated on the River Kennet and the Kennet and Avon Canal.
  • B. Hensel
    Hensel is a German surname most notably associated with mathematician Kurt Hensel, known for introducing p-adic numbers.
  • C. Hartung
    Hartung is a German surname borne by various notable individuals across fields such as art, sports, and politics.
  • D. Gamelin
    Gamelin is a French surname most notably associated with General Maurice Gamelin, the commander-in-chief of the French Army at the start of World War II.
  • E. Hilbert
    Hilbert is the male player character and primary protagonist from the Pokémon Black and White video games in the fifth generation of the Pokémon series.
  • F. None of above.

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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1850fe5348190b42259595d82cff4 completed April 29, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2b8e994819086dbfa0936898360 completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bfbc5b19c8190aed3f1199410b996 completed May 19, 2026, 5:57 a.m.
NED2 Entity disambiguation (via description) batch_6a0bfccedf2c8190833df43ea2c294ca completed May 19, 2026, 6:01 a.m.
Created at: April 17, 2026, 3:53 p.m.