Triple
T21633885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crosskeys |
E533903
|
entity |
| Predicate | ceremonialCounty |
P2713
|
FINISHED |
| Object | Gwent |
—
|
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: Gwent | Statement: [Crosskeys, ceremonialCounty, Gwent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwent Context triple: [Crosskeys, ceremonialCounty, Gwent]
-
A.
Gwent
chosen
Gwent is a historic county and preserved county in southeast Wales, known for its industrial towns and proximity to the Severn Estuary.
-
B.
Chaintré
Chaintré is a small wine-producing commune in eastern France’s Burgundy region, known for its vineyards and proximity to other notable Mâconnais villages.
-
C.
Trefl
Trefl is a Polish company best known for producing jigsaw puzzles, board games, and playing cards.
-
D.
Dominions
Dominions are a high order of angels in Christian angelology, traditionally depicted as celestial beings who regulate the duties of lower angels and maintain divine order.
-
E.
Dominion
Dominion is an alternate-history thriller novel by C.J. Sansom that imagines a Britain that made peace with Nazi Germany during World War II.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef52192e388190a3f316e33f452561 |
completed | April 27, 2026, 12:10 p.m. |
Created at: April 16, 2026, 6:35 p.m.