Triple

T7241564
Position Surface form Disambiguated ID Type / Status
Subject Hugo Carmody E155367 entity
Predicate loveInterestOf P7325 FINISHED
Object Millicent Threepwood E650561 NE FINISHED

How this triple was built (2 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: Millicent Threepwood | Statement: [Hugo Carmody, loveInterestOf, Millicent Threepwood]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millicent Threepwood
Context triple: [Hugo Carmody, loveInterestOf, Millicent Threepwood]
  • A. Millicent Threepwood chosen
    Millicent Threepwood is a recurring Wodehouse heroine from the Blandings Castle stories, known as Lord Emsworth’s spirited and intelligent niece and the love interest of Hugo Carmody.
  • B. Susan Grantly
    Susan Grantly is a fictional character in Anthony Trollope’s Barsetshire novels, known as the devoted wife of Archdeacon Theophilus Grantly.
  • C. Edith Murgatroyd
    Edith Murgatroyd was a British actress active during the silent film era, known for her role in early 1920s cinema.
  • D. Mrs Spottsworth
    Mrs Spottsworth is a wealthy, eccentric American widow in P. G. Wodehouse’s Jeeves universe, best known for her comic entanglements and romantic misadventures.
  • E. Ambrosine Phillpotts
    Ambrosine Phillpotts was a British character actress known for her numerous supporting roles in mid-20th-century film, theatre, and television.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c688143bfc81908d4176617735e601 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea552a688190a00f5d0ad982f787 completed March 27, 2026, 8:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d38efa4c8190abd6434188d8c58f completed March 28, 2026, 1:11 p.m.
Created at: March 27, 2026, 2:55 p.m.