Triple
T37607407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gliese 581e |
E935691
|
entity |
| Predicate | hostStarCatalogName |
P123592
|
FINISHED |
| Object | Gliese 581 |
—
|
NE NERFINISHED |
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: Gliese 581 | Statement: [Gliese 581e, hostStarCatalogName, Gliese 581]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostStarCatalogName Context triple: [Gliese 581e, hostStarCatalogName, Gliese 581]
-
A.
hostStarCatalog
chosen
Indicates that a celestial object’s host star is listed or identified within a specific astronomical catalog.
-
B.
hostStarHRDesignation
Indicates that a host star is associated with a specific Henry Draper (HR) catalog designation identifying it.
-
C.
starKnownAs
Indicates that a particular star is referred to or identified by a specific name or designation.
-
D.
hostStarHDDesignation
Indicates that a celestial object’s host star is identified by a specific Henry Draper (HD) catalog designation.
-
E.
hostStarAlternativeName
Indicates that an alternative or secondary name is assigned to a given host star.
- 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_69f76ed0a85481909254a8a89090c826 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb084760c8190a1554985d3c3cb7a |
completed | May 6, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69fbadf3cb548190ba3b7514f76b790a |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.