Triple
T19649010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Keeble |
E471757
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Keeble |
—
|
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: Keeble | Statement: [John Keeble, familyName, Keeble]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keeble Context triple: [John Keeble, familyName, Keeble]
-
A.
Keeble
chosen
Keeble is a fictional aristocratic surname most notably associated with Lady Constance Keeble in P. G. Wodehouse’s Blandings Castle stories.
-
B.
Killick
Killick is the irascible yet fiercely loyal steward and servant to Captain Jack Aubrey in Patrick O’Brian’s Aubrey–Maturin naval novels.
-
C.
Barnard Rubble
Barnard "Barney" Rubble is a main character from the animated television series "The Flintstones," known as Fred Flintstone’s cheerful best friend and neighbor in the prehistoric town of Bedrock.
-
D.
Tukker
Tukker is a given name or surname that functions as a variant spelling of the name Tucker.
-
E.
Brunost
Brunost is a traditional Norwegian brown whey cheese known for its caramel-like flavor and fudge-like texture.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641278e9881909bdf8d440ef6eba4 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.