Triple

T4496376
Position Surface form Disambiguated ID Type / Status
Subject Harrison Tweed E100705 entity
Predicate hasFamilyName P18 FINISHED
Object Tweed
Tweed is a surname of Scottish origin most commonly associated with the River Tweed region and borne by various notable individuals.
E446317 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: Tweed | Statement: [Harrison Tweed, hasFamilyName, Tweed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tweed
Context triple: [Harrison Tweed, hasFamilyName, Tweed]
  • A. Tweed
    Tweed is a state electoral district in New South Wales, Australia, encompassing the coastal region around Tweed Heads near the Queensland border.
  • B. Cotten
    Cotten is a surname most notably associated with American actor Joseph Cotten, a prominent figure in classic Hollywood cinema.
  • C. Mackintosh
    Mackintosh is a Scottish surname most famously associated with architect and designer Charles Rennie Mackintosh, a key figure in the Art Nouveau and Glasgow Style movements.
  • D. Loonse denier
    The Loonse denier was a medieval silver coin used as the primary monetary unit in the County of Loon in what is now Belgium.
  • E. Loden
    Loden is a surname most notably associated with Barbara Loden, the American actress and filmmaker known for her groundbreaking independent film "Wanda."
  • 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: Tweed
Triple: [Harrison Tweed, hasFamilyName, Tweed]
Generated description
Tweed is a surname of Scottish origin most commonly associated with the River Tweed region and borne by various notable individuals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tweed
Target entity description: Tweed is a surname of Scottish origin most commonly associated with the River Tweed region and borne by various notable individuals.
  • A. Tweed
    Tweed is a state electoral district in New South Wales, Australia, encompassing the coastal region around Tweed Heads near the Queensland border.
  • B. Cotten
    Cotten is a surname most notably associated with American actor Joseph Cotten, a prominent figure in classic Hollywood cinema.
  • C. Mackintosh
    Mackintosh is a Scottish surname most famously associated with architect and designer Charles Rennie Mackintosh, a key figure in the Art Nouveau and Glasgow Style movements.
  • D. Loonse denier
    The Loonse denier was a medieval silver coin used as the primary monetary unit in the County of Loon in what is now Belgium.
  • E. Loden
    Loden is a surname most notably associated with Barbara Loden, the American actress and filmmaker known for her groundbreaking independent film "Wanda."
  • 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_69bd43cdf15081909a4fa2585ff63b3e completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd56bf3ff48190b3aae0136d7fce45 completed March 20, 2026, 2:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd67c4e7c88190b9b9cab49444b515 completed March 20, 2026, 3:29 p.m.
NEDg Description generation batch_69bd683417b08190bc4e08638a30c0ec completed March 20, 2026, 3:31 p.m.
NED2 Entity disambiguation (via description) batch_69bd68b4681c8190abb170ccb054cd05 completed March 20, 2026, 3:33 p.m.
Created at: March 20, 2026, 1 p.m.