Triple
T22838455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Last Orders |
E566009
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Kate Williams |
—
|
NE NERFINISHED |
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: Kate Williams | Statement: [Last Orders, editedBy, Kate Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kate Williams Context triple: [Last Orders, editedBy, Kate Williams]
-
A.
Kate Williams
chosen
Kate Williams is a British historian, author, and television presenter known for her works on royal history and biography.
-
B.
Kate Williams
Kate Williams is a film editor known for her work on the acclaimed independent drama "Frozen River."
-
C.
Karen Williams
Karen Williams is an Australian local government politician who has served as the long-term mayor of Redland City in Queensland.
-
D.
Kate Wetherall
Kate Wetherall is a brave, resourceful, and acrobatic young girl who is one of the central child protagonists in Trenton Lee Stewart’s fantasy adventure series *The Books of Beginning*.
-
E.
Amy Williams
Amy Williams is a British skeleton racer who won the gold medal at the 2010 Winter Olympics in Vancouver.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e8244dc819089c0a7525fb512ab |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.