Triple
T4108263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Davis |
E88506
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Davies |
E71122
|
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: Davies | Statement: [Davis, hasVariant, Davies]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Davies Context triple: [Davis, hasVariant, Davies]
-
A.
Davies
chosen
Davies is a common Welsh-origin surname borne by numerous notable individuals across fields such as literature, politics, sports, and entertainment.
-
B.
Jack Davies
Jack Davies was a British screenwriter and script editor known for his work on numerous mid-20th-century films and television productions.
-
C.
Peter Davies
Peter Davies is a film editor best known for his work on the James Bond movie "A View to a Kill."
-
D.
Bob Davies
Bob Davies was an American Hall of Fame point guard renowned for leading the Rochester Royals to early professional basketball success in the 1940s and 1950s.
-
E.
Roger Davies
Roger Davies is an actor known for his role in the science fiction horror film "The Cloverfield Paradox."
- 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_69aed9484fb881909146f4c772ad277c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af019e23c481909578eba1c9270282 |
completed | March 9, 2026, 5:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b8240248190afd026a450958d4c |
completed | March 14, 2026, 2:06 p.m. |
Created at: March 9, 2026, 3:40 p.m.