Triple
T9591959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuiper Belt |
E231441
|
entity |
| Predicate | majorSourceOf |
P32799
|
FINISHED |
| Object | Jupiter-family comets |
E15968
|
NE 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: Jupiter-family comets | Statement: [Kuiper Belt, majorSourceOf, Jupiter-family comets]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jupiter-family comets Context triple: [Kuiper Belt, majorSourceOf, Jupiter-family comets]
-
A.
Comets
The Comets are the athletic teams representing Capital University in intercollegiate sports.
-
B.
Comets
The Comets is the nickname for the athletic teams representing the University of Texas at Dallas in collegiate sports.
-
C.
Cometes
Cometes is a figure in Greek mythology known primarily as the father of Thestius, a king of Aetolia.
-
D.
Kuiper Belt objects
chosen
Kuiper Belt objects are icy celestial bodies orbiting the Sun beyond Neptune, thought to be remnants from the early solar system and the source of many short-period comets.
-
E.
Dibiasky comet
The Dibiasky comet is the fictional, Earth-destroying comet central to the plot of the satirical disaster film "Don't Look Up."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8482884481908eccdfdf64d6fbf7 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a10b85881908bfc783dcb7170aa |
completed | April 1, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1618dfb688190bddd93c51bb6df41 |
completed | April 4, 2026, 7:07 p.m. |
Created at: March 30, 2026, 8:06 p.m.