Triple
T1415199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buxton |
E31898
|
entity |
| Predicate | spaTraditionSince |
P8392
|
FINISHED |
| Object | Roman times |
—
|
LITERAL 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: Roman times | Statement: [Buxton, spaTraditionSince, Roman times]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spaTraditionSince Context triple: [Buxton, spaTraditionSince, Roman times]
-
A.
traditionSince
chosen
Indicates that a tradition has been continuously practiced or recognized starting from a specified point in time.
-
B.
traditionInheritedFrom
Indicates that a tradition has been passed down or derived from an earlier source, group, or culture.
-
C.
placesInTradition
Indicates that one entity is situated, interpreted, or understood within the context or framework of a particular tradition.
-
D.
hasTraditionIn
Indicates that a particular tradition, custom, or longstanding practice is present, observed, or established within a specified place, group, or context.
-
E.
sharesTraditionsWith
Indicates that two entities have customs, practices, or cultural traditions in common or mutually observe similar traditional activities.
- F. None of above.
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_69a49919a994819086528951bc224775 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c402b1648190b87802d9beb2712e |
completed | March 1, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69a4bf060b0081909ba00e6ac093a28b |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.