Triple
T23244497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 畢宿五 |
E581546
|
entity |
| Predicate | 與畢宿星團關係 |
P69919
|
FINISHED |
| Object | 前景星，非真正成員 |
—
|
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: 前景星，非真正成員 | Statement: [畢宿五, 與畢宿星團關係, 前景星，非真正成員]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 與畢宿星團關係 Context triple: [畢宿五, 與畢宿星團關係, 前景星，非真正成員]
-
A.
associatedStarCluster
Indicates that one entity is related to or grouped with a particular star cluster, such as being part of, located in, or otherwise linked to that cluster.
-
B.
associatedGlobularCluster
Indicates that one entity is linked or connected to a particular globular cluster in an astronomically relevant way.
-
C.
belongsToStarCluster
Indicates that an astronomical object is a member of, or gravitationally bound to, a specific star cluster.
-
D.
isForegroundStarOfCluster
chosen
Indicates that a star lies in the foreground along the line of sight to a star cluster, rather than being physically associated with the cluster itself.
-
E.
isOneOfNearestOpenClustersToEarth
Indicates that the subject cluster is among the closest open star clusters to Earth in terms of spatial distance.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193ee37c8819091f799506fa532da |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.