Triple
T32141739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sérsic index |
E820922
|
entity |
| Predicate | usedAsProxyFor |
P2506
|
FINISHED |
| Object | galaxy concentration index |
—
|
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: galaxy concentration index | Statement: [Sérsic index, usedAsProxyFor, galaxy concentration index]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsProxyFor Context triple: [Sérsic index, usedAsProxyFor, galaxy concentration index]
-
A.
isUsedAs
chosen
Indicates that one entity serves a particular function, role, or purpose as another entity.
-
B.
usedByFor
Indicates that one entity makes use of another entity for a specific purpose or function.
-
C.
usedVia
Indicates that an entity performs or achieves something by means of, or through the use of, another entity or mechanism.
-
D.
usedAsParentFor
Indicates that one entity functions as the parent or container for another entity within a hierarchical or structural relationship.
-
E.
usedAsAuthorityFor
Indicates that one entity is relied upon as an authoritative source or reference for validating, justifying, or supporting another entity.
- 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd864235b481908738dbb69556bc62 |
completed | May 8, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69fd8373b6bc819091c554f29ee17fec |
completed | May 8, 2026, 6:32 a.m. |
Created at: May 1, 2026, 12:30 a.m.