Triple
T20914402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mother Hill |
E515032
|
entity |
| Predicate | roadClosed |
P120271
|
FINISHED |
| Object | A625 abandoned across landslip in 1979 |
—
|
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: A625 abandoned across landslip in 1979 | Statement: [Mother Hill, roadClosed, A625 abandoned across landslip in 1979]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadClosed Context triple: [Mother Hill, roadClosed, A625 abandoned across landslip in 1979]
-
A.
roadClosedReason
Indicates the reason why a particular road is closed.
-
B.
closedToAllTraffic
chosen
Indicates that the subject is not accessible or usable by any type of traffic.
-
C.
closedToThroughTraffic
Indicates that a route or area is not accessible for general passage and cannot be used as a through route for traffic.
-
D.
roadAffected
Indicates that a road is impacted or disrupted by a condition, event, or action, such as construction, accidents, or adverse weather.
-
E.
closedToTrafficDuringRepairs
Indicates that an entity (such as a road or route) is not accessible for traffic for the duration of repair or maintenance work.
- 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec61a6ec81908d9e0629438d27c9 |
completed | April 21, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c9ac91108190a6700fcdf2f11890 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:48 p.m.