Triple
T13904929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shard Bridge |
E334322
|
entity |
| Predicate | riverMilepost |
P111954
|
FINISHED |
| Object | lower reaches of River Wyre |
—
|
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: lower reaches of River Wyre | Statement: [Shard Bridge, riverMilepost, lower reaches of River Wyre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverMilepost Context triple: [Shard Bridge, riverMilepost, lower reaches of River Wyre]
-
A.
riverMileFromMouth
Indicates the distance, measured in river miles, from the river’s mouth upstream to a specific point along the river.
-
B.
riverLocation
Indicates that a river is located in, passes through, or is geographically associated with a specified place or region.
-
C.
riverKilometerContext
Indicates the position or context of something along a river, measured in river kilometers from a defined reference point.
-
D.
trailMilepostOn
Indicates that a specific milepost is physically located on and associated with a particular trail segment or trail route.
-
E.
approximateMileMarker
Indicates an estimated or not precisely measured position along a route expressed in miles.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25db1e308190aaed6a21e443cc44 |
completed | April 14, 2026, 11:32 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
| PDg | Predicate description generation | batch_69de01ed2098819088ec45069f6f2609 |
completed | April 14, 2026, 8:59 a.m. |
Created at: April 9, 2026, 10:16 p.m.