Triple
T29865382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siemens SWT-2.3-93 |
E758440
|
entity |
| Predicate | nacelleMounting |
P87015
|
FINISHED |
| Object | tubular steel tower |
—
|
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: tubular steel tower | Statement: [Siemens SWT-2.3-93, nacelleMounting, tubular steel tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nacelleMounting Context triple: [Siemens SWT-2.3-93, nacelleMounting, tubular steel tower]
-
A.
typicalTurbineMounting
chosen
Indicates the usual or standard way in which a turbine is mounted or installed relative to its supporting structure.
-
B.
nacelleSupplier
Indicates that one entity serves as the supplier or provider of nacelles to another entity.
-
C.
aircraftEngineMounting
Indicates that an aircraft engine is attached or secured to a supporting structure or mounting point on the aircraft.
-
D.
bellMounting
Indicates that one entity is mounted, fixed, or installed as a bell onto another supporting structure or surface.
-
E.
hasNacelles
Indicates that an object is equipped with one or more nacelles attached to it.
- 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67688760481908e28d887d583e8c4 |
completed | May 2, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:51 p.m.