Triple
T7654867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Street (Cardiff) |
E173353
|
entity |
| Predicate | hasRoadNumberStatus |
P78582
|
FINISHED |
| Object | unclassified city street |
—
|
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: unclassified city street | Statement: [Castle Street (Cardiff), hasRoadNumberStatus, unclassified city street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoadNumberStatus Context triple: [Castle Street (Cardiff), hasRoadNumberStatus, unclassified city street]
-
A.
hasConnectingRoadNumber
Indicates that there exists a road connection between two locations or road segments identified by a specific road number.
-
B.
hasRoadStandard
Indicates that a road or roadway segment conforms to, or is governed by, a specific road design, construction, or operational standard.
-
C.
hasRoadPass
Indicates that an entity possesses a valid authorization or permit required to use a specific road or road network.
-
D.
hasRoadSuffix
Indicates that a road or street name ends with a specific suffix (such as "Street", "Avenue", or "Boulevard").
-
E.
hasRoadway
Indicates that one location or area is connected to another by a road or roadway infrastructure.
- 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_69c6995473348190a4f41d110d619a18 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7061cbc3c8190a917dd7e71214182 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015dd8fc8190bc5f52a12bd46209 |
completed | March 27, 2026, 10:14 p.m. |
| PDg | Predicate description generation | batch_69c7061b218c81909fff789ba4c10e58 |
completed | March 27, 2026, 10:35 p.m. |
Created at: March 27, 2026, 3:59 p.m.