Triple
T32023870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IM Pegasi |
E817765
|
entity |
| Predicate | massSecondary |
P146047
|
FINISHED |
| Object | ~1 solar mass (approx) |
—
|
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: ~1 solar mass (approx) | Statement: [IM Pegasi, massSecondary, ~1 solar mass (approx)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: massSecondary Context triple: [IM Pegasi, massSecondary, ~1 solar mass (approx)]
-
A.
hasMassSecondary
Indicates that an entity possesses or is associated with the mass value of a secondary object or component in a system.
-
B.
massOfPrimary
Indicates the mass value associated with the primary object in a relationship or system.
-
C.
massOfSecondaryComponent
chosen
Indicates the mass value associated specifically with the secondary component in a composite or multi-part system.
-
D.
massFront
Indicates that one entity is positioned directly in front of or facing the front side of another entity in terms of mass or physical arrangement.
-
E.
massCategory
Indicates the classification of an entity based on its mass into a defined category or range.
- 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_69f348fb04e4819081f4eab040ed7959 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b4684000819090d1f2f28af40db9 |
completed | May 3, 2026, 2:35 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:17 a.m.