Triple
T4617697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Double Cluster |
E100905
|
entity |
| Predicate | hasApproximateStarCount |
P7300
|
FINISHED |
| Object | several hundred stars per cluster |
—
|
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: several hundred stars per cluster | Statement: [Double Cluster, hasApproximateStarCount, several hundred stars per cluster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateStarCount Context triple: [Double Cluster, hasApproximateStarCount, several hundred stars per cluster]
-
A.
starCount
Indicates the number of stars associated with an entity, typically representing a rating, quality level, or count of starred items.
-
B.
approximateStellarCount
chosen
Indicates an estimated or rough number of stars associated with a given astronomical object or region.
-
C.
hasStarOn
Indicates that one entity bears or displays a star symbol positioned on another entity.
-
D.
hasMetascore
Indicates that an entity is associated with a Metascore rating, typically representing an aggregated critical review score.
-
E.
numberOfStarsInConstellation
Indicates the numerical count of stars that belong to a given constellation.
- 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_69bd43cf363c819087fd5ab441b4a3f4 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd59e098c08190b769e76937dff700 |
completed | March 20, 2026, 2:29 p.m. |
| PD | Predicate disambiguation | batch_69bd522fd5c48190ad2bffc0a5bc9061 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.