Triple
T3587585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ESO 3.6 m Telescope |
E75947
|
entity |
| Predicate | clearAperture |
P12152
|
FINISHED |
| Object | 3.6 metres |
—
|
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: 3.6 metres | Statement: [ESO 3.6 m Telescope, clearAperture, 3.6 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clearAperture Context triple: [ESO 3.6 m Telescope, clearAperture, 3.6 metres]
-
A.
hasAperture
chosen
Indicates that one entity possesses or is characterized by a specific opening, gap, or aperture.
-
B.
clearingSystem
Indicates that one entity functions as the financial clearing mechanism or infrastructure used to settle transactions for another entity.
-
C.
hasApertureClass
Indicates that one entity is classified according to a specific aperture category or class of another entity.
-
D.
rearCameraAperture
Indicates the size or f-stop value of the aperture used by a device’s rear-facing camera when capturing images or video.
-
E.
apexOriginallyCappedBy
Indicates that the topmost point or peak of something was initially covered, sealed, or finished with a particular cap or crowning element.
- 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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc13a11608190a23d76efc1b50e3c |
completed | March 8, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69adb839b4e08190b1c0d611cccb11ae |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:22 p.m.