Triple
T13016597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Watford Locks |
E322567
|
entity |
| Predicate | connectsLevel |
P845
|
FINISHED |
| Object | lower level of Grand Union Canal |
—
|
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 level of Grand Union Canal | Statement: [Watford Locks, connectsLevel, lower level of Grand Union Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsLevel Context triple: [Watford Locks, connectsLevel, lower level of Grand Union Canal]
-
A.
upperLevelConnects
Indicates a connection where one entity links to or interfaces with another at a higher or superior level in a hierarchy or structure.
-
B.
connectsUnder
Indicates that one entity forms a connection to another entity by passing beneath or under it.
-
C.
connectsTo
chosen
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
D.
connectsRole
Indicates a relationship in which one entity is linked to another by assigning or associating a specific role between them.
-
E.
connectsState
Indicates a relationship where one entity serves as a link or conduit between different states, conditions, or statuses of another entity.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecd04748190ade2530ee5db35fe |
completed | April 10, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69d97dc39a0881908119c62e31bf6182 |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 8:51 p.m.