Triple
T9808985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IR G102 grism |
E238220
|
entity |
| Predicate | dispersionDirection |
P90120
|
FINISHED |
| Object | approximately along detector x-axis |
—
|
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 along detector x-axis | Statement: [IR G102 grism, dispersionDirection, approximately along detector x-axis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dispersionDirection Context triple: [IR G102 grism, dispersionDirection, approximately along detector x-axis]
-
A.
dispersionType
Indicates the manner or pattern in which something is spread, scattered, or distributed relative to something else.
-
B.
dispersion
Indicates the degree to which items in a set are spread out or scattered relative to one another.
-
C.
dispersalVector
Indicates the means or agent by which something (such as an organism, propagule, or substance) is spread or transported from one location to another.
-
D.
dispersingElement
Indicates that one entity causes another entity to spread out or scatter from a concentrated state into a wider area or among multiple parts.
-
E.
separatesDirection
Indicates that one entity divides or distinguishes different directions or directional paths from each other.
- 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_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. |
| PDg | Predicate description generation | batch_69cd06abc9248190a506b64e9c516d03 |
completed | April 1, 2026, 11:51 a.m. |
Created at: March 30, 2026, 8:29 p.m.