Triple
T1709665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bay Bridge |
E36948
|
entity |
| Predicate | upperDeckDirection |
P32216
|
FINISHED |
| Object | westbound (current configuration) |
—
|
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: westbound (current configuration) | Statement: [Bay Bridge, upperDeckDirection, westbound (current configuration)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upperDeckDirection Context triple: [Bay Bridge, upperDeckDirection, westbound (current configuration)]
-
A.
offsetDirection
Indicates the relative direction in which one entity is displaced or shifted from another reference entity.
-
B.
transportDirection
Indicates the directional flow or route along which something is transported from an origin toward a destination.
-
C.
hasUpperFloor
Indicates that one entity possesses or includes an upper floor relative to another level or reference point.
-
D.
frontLineDirection
Indicates the primary orientation or bearing in which the front line of a conflict, formation, or boundary is facing or advancing.
-
E.
upperDeckLanes
Indicates that the related entities are lanes located on the upper deck level of a multi-level structure (such as a roadway, bridge, or parking facility).
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab7521878c8190b9e7739b8c3fc705 |
completed | March 7, 2026, 12:45 a.m. |
| PD | Predicate disambiguation | batch_69aa61bd46d48190915500d75a9d8e94 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69ab752034348190a1cc20955ed24f6f |
completed | March 7, 2026, 12:45 a.m. |
Created at: March 4, 2026, 7:30 p.m.