Triple
T33900048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Messier 72 |
E869020
|
entity |
| Predicate | hasNearbyObjectOnSky |
P133149
|
FINISHED |
| Object | Messier 73 |
—
|
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: Messier 73 | Statement: [Messier 72, hasNearbyObjectOnSky, Messier 73]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyObjectOnSky Context triple: [Messier 72, hasNearbyObjectOnSky, Messier 73]
-
A.
nearbyObjectOnSky
chosen
Indicates that one object appears close to another object in the sky, as observed from a given viewpoint.
-
B.
hasDeepSkyObject
Indicates that an entity is associated with or contains a specific deep-sky astronomical object (such as a galaxy, nebula, or star cluster).
-
C.
hasNearbyObservatories
Indicates that one entity has one or more observatories located in close geographic proximity to it.
-
D.
isObservedNear
Indicates that one entity is detected or noticed in close spatial proximity to another entity.
-
E.
isUsedAsReferencePointInNightSky
Indicates that something serves as a positional or navigational reference point when observing or orienting in the night sky.
- 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_69f34997703c8190866b1d404bce531f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff9a25407c81909faa86e72a7a9d17 |
completed | May 9, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69ff99c613688190a03b2f93d5ccad2b |
completed | May 9, 2026, 8:32 p.m. |
Created at: May 1, 2026, 1:48 a.m.