Triple
T19619408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardrishaig |
E470957
|
entity |
| Predicate | harbourFunction |
P12053
|
FINISHED |
| Object | gateway to Crinan 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: gateway to Crinan Canal | Statement: [Ardrishaig, harbourFunction, gateway to Crinan Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: harbourFunction Context triple: [Ardrishaig, harbourFunction, gateway to Crinan Canal]
-
A.
harbourUse
chosen
Indicates how a harbour is used or purposed, such as for specific activities, functions, or types of maritime operations.
-
B.
harbor
Indicates providing shelter, protection, or refuge for someone or something, often by keeping them in a safe or hidden place.
-
C.
harbourAspect
Indicates that one entity serves as a contextual or environmental aspect influencing the state, behavior, or interpretation of another entity.
-
D.
startHarbour
Indicates that an entity serves as the starting harbor or port of departure for a journey or route.
-
E.
servedHarbour
Indicates that an entity provided service, support, or functions related to a harbour or port.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e4570c81909fc4f9b871346337 |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.