Triple
T22279615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRAS redshift survey |
E550695
|
entity |
| Predicate | selectsObjectsBy |
P96483
|
FINISHED |
| Object | infrared flux |
—
|
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: infrared flux | Statement: [IRAS redshift survey, selectsObjectsBy, infrared flux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectsObjectsBy Context triple: [IRAS redshift survey, selectsObjectsBy, infrared flux]
-
A.
selectsFor
Indicates that one entity chooses or designates another entity as the preferred or targeted option from a set of possible candidates.
-
B.
selectedWith
Indicates that one entity is chosen or picked in conjunction with, or as part of a set including, another entity.
-
C.
selectsMembersBy
chosen
Indicates that an entity chooses or designates specific members from a larger group or collection based on some criteria.
-
D.
selectionFrom
Indicates that one entity is chosen as a member or subset from a larger set or collection represented by another entity.
-
E.
selectionComponents
Indicates that certain elements function as constituent parts or options within a larger selection or choice.
- 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_69e11e44d538819097c6b8f333af3352 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14eaa8cec819081c2ad031154ebe7 |
completed | April 29, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e72ff0363081909f794d19c8a64837 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:40 p.m.