Triple
T30640965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loch Torridon |
E779975
|
entity |
| Predicate | hasOuterPart |
P118374
|
FINISHED |
| Object | Outer Loch Torridon |
—
|
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: Outer Loch Torridon | Statement: [Loch Torridon, hasOuterPart, Outer Loch Torridon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOuterPart Context triple: [Loch Torridon, hasOuterPart, Outer Loch Torridon]
-
A.
hasOuterLayer
chosen
Indicates that one entity forms the external or surrounding layer of another entity.
-
B.
hasOuterLayers
Indicates that one entity possesses external layers or coverings surrounding its main body or structure.
-
C.
hasOuterStructure
Indicates that one entity possesses or is characterized by an external or surrounding structural component formed by another entity.
-
D.
hasUpperPartFrom
Indicates that an entity includes, incorporates, or is composed of an upper part originating from another entity.
-
E.
hasFirstPart
Indicates that one entity is the initial or earliest part, segment, or component of another entity in an ordered whole.
- 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_69f224a50ebc81909b961a94c7f66b12 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6b967d5308190bbb66d0a8dd52612 |
completed | May 3, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69f6b6293188819080d5041ca0adb969 |
completed | May 3, 2026, 2:42 a.m. |
Created at: April 29, 2026, 8:29 p.m.