Triple
T33212192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OSIRIS-APEX |
E850189
|
entity |
| Predicate | preApophisTarget |
P176194
|
FINISHED |
| Object | asteroid Bennu |
—
|
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: asteroid Bennu | Statement: [OSIRIS-APEX, preApophisTarget, asteroid Bennu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preApophisTarget Context triple: [OSIRIS-APEX, preApophisTarget, asteroid Bennu]
-
A.
closestApproachTarget
Indicates the entity that another entity comes nearest to during its path or motion.
-
B.
isPotentiallyHazardousAsteroid
Indicates that an asteroid poses a potential risk of causing significant harm or damage, typically due to its size and proximity to a planet or other celestial body.
-
C.
apoapsisType
Indicates the specific kind or classification of an orbit’s apoapsis (farthest point from the central body) associated with an entity.
-
D.
hasAphelionNear
Indicates that one celestial body's aphelion (its farthest point from the object it orbits) lies close to another specified reference point or object.
-
E.
apoapsisBody
Indicates the celestial body that an orbiting object is farthest from at its apoapsis.
- F. None of above. chosen
Provenance (4 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_69f3495fb92c819083ce65d0ddee7a76 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6dd3cc0648190a275812d6711275a |
completed | May 3, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69f6d82eaee081908f06a71546315aea |
completed | May 3, 2026, 5:07 a.m. |
| PDg | Predicate description generation | batch_69f6dd3b335481909e24d4eb5b0269f9 |
completed | May 3, 2026, 5:29 a.m. |
Created at: May 1, 2026, 1:30 a.m.