Triple
T24657006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarbat Ness Lighthouse |
E610419
|
entity |
| Predicate | focalHeightMetres |
P61254
|
FINISHED |
| Object | 53 |
—
|
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: 53 | Statement: [Tarbat Ness Lighthouse, focalHeightMetres, 53]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focalHeightMetres Context triple: [Tarbat Ness Lighthouse, focalHeightMetres, 53]
-
A.
focalLength
Indicates the distance between a lens or mirror and its focal point, determining how strongly it converges or diverges light.
-
B.
focalPlaneHeight
chosen
Indicates the vertical distance or elevation of the focal plane relative to a defined reference level or surface.
-
C.
hasFocalRatio
Indicates a relationship where an optical system is associated with a specific focal ratio (f-number) that characterizes its light-gathering speed and image brightness.
-
D.
depthMetresApprox
Indicates an approximate measurement of how deep something is in metres, rather than an exact value.
-
E.
hasFocalPlane
Indicates that an optical system or imaging device possesses a specific focal plane where light is brought into focus.
- 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_69e2c4d453248190a020354e93ef6282 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f41011d8048190be70329ba0bfb7c7 |
completed | May 1, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69f40ed9d47881909fcfc0d04e8d074a |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 2:34 a.m.