Triple
T37756069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurleston Junction |
E941115
|
entity |
| Predicate | lockFlightLeadsTo |
P59549
|
FINISHED |
| Object | Llangollen Canal |
—
|
NE NERFINISHED |
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: Llangollen Canal | Statement: [Hurleston Junction, lockFlightLeadsTo, Llangollen Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lockFlightLeadsTo Context triple: [Hurleston Junction, lockFlightLeadsTo, Llangollen Canal]
-
A.
lockFlightName
Indicates that a specific flight’s name or identifier is fixed and cannot be changed.
-
B.
hasLockFlight
chosen
Indicates that one entity is associated with a specific lock flight, representing a relationship where the entity uses, contains, or is located at that sequence of canal locks.
-
C.
lockFlightOrientation
Indicates that an entity constrains or fixes another entity’s flight orientation so it cannot freely change its attitude or direction.
-
D.
numberOfLocksInMainFlight
Indicates the total count of locks present in the main flight (primary sequence) of a canal or lock system.
-
E.
associatedWithFlight
Indicates a relationship where an entity is linked or connected to a specific flight, such as by participation, operation, or relevance.
- 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_69f76ee1f3a88190834e6c8af99bccc9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaef51da881909c03d1dc36422ce7 |
completed | May 6, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69fbadf632ec8190b14991c971258307 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:19 p.m.