Triple
T220056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GA 85 |
E4192
|
entity |
| Predicate | directionA |
P3915
|
FINISHED |
| Object | South |
—
|
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: South | Statement: [GA 85, directionA, South]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionA Context triple: [GA 85, directionA, South]
-
A.
orientation
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
B.
directed
Indicates that one entity served as the director or guiding authority responsible for overseeing and controlling the actions or production involving another entity.
-
C.
hasTrafficDirection
Indicates that there is a specified flow or orientation of traffic associated with an entity (such as a road, lane, or route).
-
D.
positionA
Indicates the spatial or ordered position of an entity A within a defined reference frame or sequence.
-
E.
trafficDirection
chosen
Indicates the direction in which traffic is intended or allowed to move relative to a given reference point or segment.
- 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_69a2573508588190b522c2476d91acfe |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25efd0df48190b8fef4c422a1265f |
completed | Feb. 28, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69a25b54d790819093b35bd1a6f00f92 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.