Triple
T29768541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | V399 Carinae |
E753982
|
entity |
| Predicate | radiusCategory |
P167864
|
FINISHED |
| Object | very large stellar radius |
—
|
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: very large stellar radius | Statement: [V399 Carinae, radiusCategory, very large stellar radius]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: radiusCategory Context triple: [V399 Carinae, radiusCategory, very large stellar radius]
-
A.
ringRadius
Indicates the size of a ring by specifying the distance from its center to its outer edge.
-
B.
distanceCategory
Indicates the qualitative classification of how far apart two entities are from each other (e.g., near, medium, far).
-
C.
rankingCategory
Indicates the classification or type of ranking under which an entity is evaluated or ordered.
-
D.
ratingCategory
Indicates the qualitative classification or level assigned to a rating (e.g., low, medium, high) within an evaluation or scoring system.
-
E.
mapsRadiusRTo
Indicates a relationship where one entity maps or transforms elements within a radius R around a point in one space to corresponding elements in another space.
- 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_69f0ef827ff88190ade56e0b0846b713 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f6745f8354819085a81de5c32dd49e |
completed | May 2, 2026, 10:02 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69f66c59de9881909ebbb7b0ae7ab495 |
completed | May 2, 2026, 9:27 p.m. |
Created at: April 28, 2026, 8:40 p.m.