Triple
T2373205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wide Field and Planetary Camera 2 |
E46135
|
entity |
| Predicate | pixelArray |
P38757
|
FINISHED |
| Object | 800 by 800 pixels per CCD |
—
|
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: 800 by 800 pixels per CCD | Statement: [Wide Field and Planetary Camera 2, pixelArray, 800 by 800 pixels per CCD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pixelArray Context triple: [Wide Field and Planetary Camera 2, pixelArray, 800 by 800 pixels per CCD]
-
A.
pixelScale
Indicates the ratio or conversion factor between pixel units and real-world or coordinate-space units in a representation or image.
-
B.
paletteSize
Indicates the number of distinct colors included in a given color palette.
-
C.
publicImage
Indicates how an entity is perceived or represented by the general public or broader audience.
-
D.
imagedIn
Indicates that one entity appears within or is depicted in an image associated with another entity.
-
E.
pegType
Indicates the specific category or kind of peg associated with or assigned to an entity.
- F. None of above. chosen
Provenance (4 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abca4d89248190be7d712d5fa8382b |
completed | March 7, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69abc59d82f08190b7c36982d1ae783d |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abca4c937c8190b4dfca716b868d4f |
completed | March 7, 2026, 6:48 a.m. |
Created at: March 4, 2026, 7:56 p.m.