Triple
T23727094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tobermory lighthouse (nearby Rubha nan Gall) |
E586305
|
entity |
| Predicate | servesHarbour |
P91691
|
FINISHED |
| Object | Tobermory harbour |
—
|
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: Tobermory harbour | Statement: [Tobermory lighthouse (nearby Rubha nan Gall), servesHarbour, Tobermory harbour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesHarbour Context triple: [Tobermory lighthouse (nearby Rubha nan Gall), servesHarbour, Tobermory harbour]
-
A.
servedHarbour
chosen
Indicates that an entity provided service, support, or functions related to a harbour or port.
-
B.
hasHarbor
Indicates that a place possesses or contains a harbor for docking or sheltering vessels.
-
C.
harbourUse
Indicates how a harbour is used or purposed, such as for specific activities, functions, or types of maritime operations.
-
D.
hasHarbourEntrance
Indicates that an entity serves as the entrance or access point to a harbour for another entity.
-
E.
associatedHarbour
Indicates a relationship where a place, route, or maritime entity is linked to or served by a particular harbour.
- 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b9167bdc81909d837e018e7d0e29 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:08 p.m.