Triple
T9602846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Diego–Coronado Bridge |
E231890
|
entity |
| Predicate | curveDescription |
P89178
|
FINISHED |
| Object | sweeping |
—
|
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: sweeping | Statement: [San Diego–Coronado Bridge, curveDescription, sweeping]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: curveDescription Context triple: [San Diego–Coronado Bridge, curveDescription, sweeping]
-
A.
curveCondition
Indicates that a specific condition or constraint applies to a curve, such as its shape, smoothness, or allowable parameter range.
-
B.
trackDescription
Indicates the descriptive information or summary text associated with a specific track (such as a song, audio piece, or recorded segment).
-
C.
surfaceDescription
Indicates that one entity provides a textual or qualitative description of the surface characteristics or appearance of another entity.
-
D.
locusDescription
Indicates how the spatial position or location of an entity is described or characterized.
-
E.
relatedCurve
Indicates that one curve is associated with or derived from another curve in a defined relational way.
- F. None of above. chosen
Provenance (4 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_69ca8484838c8190b2049199d22fef70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a5af8f0819089408ed630afa812 |
completed | April 1, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a6fd2481908efd131e207b8143 |
completed | April 1, 2026, 8:21 a.m. |
| PDg | Predicate description generation | batch_69ccd93fc45c8190a823305e461e581d |
completed | April 1, 2026, 8:37 a.m. |
Created at: March 30, 2026, 8:08 p.m.