Triple

T147592
Position Surface form Disambiguated ID Type / Status
Subject Will E3364 entity
Predicate relatedName P3889 FINISHED
Object Willy E17731 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: Willy | Statement: [Will, relatedName, Willy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Willy
Context triple: [Will, relatedName, Willy]
  • A. Willy chosen
    Willy is a common diminutive form of the given name William, often used as an informal or affectionate nickname.
  • B. Earl
    An Earl is a noble rank in the British and some European peerage systems, historically positioned below a marquess and above a viscount.
  • C. Harold
    Harold is a masculine given name of Old English origin, historically borne by several notable figures including kings and modern public personalities.
  • D. Bert
    Bert is the given name of Bert Hölldobler, a renowned German behavioral biologist and sociobiologist known for his pioneering research on ants and social insects.
  • E. Carl
    Carl is the given name of Carl Sagan, the renowned American astronomer, science communicator, and author.
  • 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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a25bab43608190ba5ebfbee6b5b6e4 completed Feb. 28, 2026, 3:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2e3bd8ee88190a708c0aa20b3c7d7 completed Feb. 28, 2026, 12:46 p.m.
Created at: Feb. 28, 2026, 2:31 a.m.