Triple
T39027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William |
E772
|
entity |
| Predicate | diminutive |
P456
|
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: [William, diminutive, Willy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Willy Context triple: [William, diminutive, 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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24ec1ef5481909daf99654dfa3f57 |
completed | Feb. 28, 2026, 2:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2c93548988190a7514e0cc2df0de4 |
completed | Feb. 28, 2026, 10:53 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.