Triple
T8297023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clayton, California |
E194244
|
entity |
| Predicate | downtownFeatures |
P78903
|
FINISHED |
| Object | small shops and restaurants |
—
|
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: small shops and restaurants | Statement: [Clayton, California, downtownFeatures, small shops and restaurants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: downtownFeatures Context triple: [Clayton, California, downtownFeatures, small shops and restaurants]
-
A.
hasDowntownCharacteristic
chosen
Indicates that something possesses a feature, quality, or attribute typically associated with a downtown area.
-
B.
hasDowntown
Indicates that a place or city possesses a central downtown area.
-
C.
nearDowntown
Indicates that one location is situated close to or within a short distance of a city’s downtown area.
-
D.
connectsDowntownTo
Indicates a relationship where one location, route, or service provides a direct connection or access to a downtown area.
-
E.
isDowntownEndpointOf
Indicates that a location serves as the downtown terminus or endpoint of a route, line, or path.
- 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_69ca82e50ebc81909aa7b260c76bd757 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7df887148190bddc2609bc885cb4 |
completed | March 31, 2026, 7:55 a.m. |
| PD | Predicate disambiguation | batch_69cb70b5b5348190b296e0ecec95de60 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:53 p.m.