Triple
T22999186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leonids |
E572587
|
entity |
| Predicate | meteorComposition |
P133479
|
FINISHED |
| Object | dust and small particles from Comet Tempel–Tuttle |
—
|
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: dust and small particles from Comet Tempel–Tuttle | Statement: [Leonids, meteorComposition, dust and small particles from Comet Tempel–Tuttle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meteorComposition Context triple: [Leonids, meteorComposition, dust and small particles from Comet Tempel–Tuttle]
-
A.
meteoriteType
Indicates the classification or category of a meteorite based on its composition or characteristics.
-
B.
meteoriteClass
Indicates the classification category or type assigned to a meteorite based on its composition or characteristics.
-
C.
dustComposition
chosen
Indicates the material makeup or constituent substances that form a given dust sample or dust population.
-
D.
meteoroidSource
Indicates that one entity is the origin or source from which the meteoroid represented by the other entity comes.
-
E.
moonMassFraction
Indicates the proportion of an object's total mass that is contained in its moon or moons.
- 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_69e245b6a3ac81908087599eefe3e365 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182f6484c8190bfe3f7ea894c43d8 |
completed | April 29, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69ef3b974e7c8190b8be11dbb4518693 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:50 p.m.