Triple
T16296765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NGC 2403 |
E395666
|
entity |
| Predicate | positionAngle |
P49681
|
FINISHED |
| Object | approximately 124 degrees |
—
|
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: approximately 124 degrees | Statement: [NGC 2403, positionAngle, approximately 124 degrees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionAngle Context triple: [NGC 2403, positionAngle, approximately 124 degrees]
-
A.
projectionAngle
Indicates the angle at which one entity is projected onto or relative to another reference (such as a line, plane, or direction).
-
B.
offAxisAngle
chosen
Indicates the angle by which something is rotated or deviates from a defined primary or reference axis.
-
C.
poleOrientation
Indicates the directional alignment or facing of a pole relative to a reference frame or coordinate system.
-
D.
angleProperty
Indicates that a relationship specifies a particular geometric or quantitative characteristic (such as measure, type, or orientation) of an angle between entities.
-
E.
depictionAngle
Indicates the angle or viewpoint from which something is visually depicted or represented.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e2dcdac819083918f0964dd5666 |
completed | April 17, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.