Triple
T15313289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Octopus |
E366091
|
entity |
| Predicate | draughtMetres |
P85505
|
FINISHED |
| Object | 5.8 |
—
|
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: 5.8 | Statement: [Octopus, draughtMetres, 5.8]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: draughtMetres Context triple: [Octopus, draughtMetres, 5.8]
-
A.
draught
Indicates that one entity is the version or serving of a beverage (typically beer) that is drawn from a cask, keg, or tap rather than from a bottle or can.
-
B.
hasDraught
chosen
Indicates that an entity has a specific vertical distance between the waterline and the lowest point of its hull or structure (its draught).
-
C.
depthMetresApprox
Indicates an approximate measurement of how deep something is in metres, rather than an exact value.
-
D.
dimensionOfLength
Indicates that something represents or specifies a measurement along a single spatial extent (a length dimension).
-
E.
dimensions_km
Indicates the physical size or extent of something measured in kilometers, typically specifying one or more linear dimensions (e.g., length, width, height).
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03cd2d5a88190aead748920f93d47 |
completed | April 16, 2026, 1:35 a.m. |
| PD | Predicate disambiguation | batch_69deca935e2c8190b640987ddfc542b9 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:16 a.m.