Triple
T6094965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saiph |
E135853
|
entity |
| Predicate | likelyRemnantType |
P57740
|
FINISHED |
| Object | neutron star or black hole |
—
|
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: neutron star or black hole | Statement: [Saiph, likelyRemnantType, neutron star or black hole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyRemnantType Context triple: [Saiph, likelyRemnantType, neutron star or black hole]
-
A.
remnantType
chosen
Indicates the specific kind or category of remnant that results from or is associated with an entity or process.
-
B.
isYoungerRemnantOf
Indicates that one entity is the surviving, younger portion or successor of another entity that existed earlier and has largely disappeared or transformed.
-
C.
remnantName
Indicates that an entity is identified by a name specifically associated with a remaining part, leftover, or surviving fragment of something previously whole.
-
D.
lastRemnantOf
Indicates that one entity is the sole remaining instance or surviving part of another entity, after all similar or related instances have disappeared.
-
E.
remnants
Indicates that parts or traces of something remain after the main portion has been removed, used, or destroyed.
- 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_69c0087cd3c48190b459848c72d84eb1 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05a963bac8190bc0c33fef187875c |
completed | March 22, 2026, 9:09 p.m. |
| PD | Predicate disambiguation | batch_69c049f5ac988190b62ba565153aaa35 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:12 p.m.