Triple
T9808977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IR G102 grism |
E238220
|
entity |
| Predicate | associatedCalibration |
P50659
|
FINISHED |
| Object | WFC3 IR flat fields |
—
|
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: WFC3 IR flat fields | Statement: [IR G102 grism, associatedCalibration, WFC3 IR flat fields]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedCalibration Context triple: [IR G102 grism, associatedCalibration, WFC3 IR flat fields]
-
A.
calibratedFor
Indicates that something has been adjusted or tuned to operate accurately or optimally for a specific target, condition, or context.
-
B.
hasCalibration
chosen
Indicates that an entity is associated with or uses a specific calibration configuration, setting, or procedure.
-
C.
calibrationAuthority
Indicates that one entity serves as the official source or authority responsible for defining, validating, or approving the calibration of another entity.
-
D.
supportsHardwareCalibration
Indicates that one entity provides the capability or functionality to perform calibration operations on another entity’s hardware.
-
E.
associatedScale
Indicates that one entity is linked or connected to a particular scale used to measure, classify, or evaluate 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb21ef32c8190ab4b09d157798451 |
completed | April 2, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.