Triple
T18956889
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NGC 6712 |
E463801
|
entity |
| Predicate | lineOfSight |
P133953
|
FINISHED |
| Object | through dense regions of the Galactic disk |
—
|
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: through dense regions of the Galactic disk | Statement: [NGC 6712, lineOfSight, through dense regions of the Galactic disk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineOfSight Context triple: [NGC 6712, lineOfSight, through dense regions of the Galactic disk]
-
A.
hasFieldOfView
Indicates that one entity possesses a visual coverage area within which it can perceive or detect other entities or regions.
-
B.
canBeSeenWith
Indicates that two entities are observable together in the same context, setting, or time.
-
C.
locationOfVision
Indicates the place or setting where a vision or visual experience occurs or is perceived.
-
D.
hasVisionTrigger
Indicates that one entity causes or initiates a vision-related response or event in another entity.
-
E.
observationArc
Indicates a relationship where one entity serves as an observational link or span over which another entity is monitored, tracked, or measured across a period or range.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5cdf2d08190a0aecd3fa5335a75 |
completed | April 20, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f437648190b85650dae8885d48 |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, noon