Triple
T8489432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Centauro II |
E200928
|
entity |
| Predicate | sightingSystems |
P81647
|
FINISHED |
| Object | day/night sights |
—
|
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: day/night sights | Statement: [Centauro II, sightingSystems, day/night sights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sightingSystems Context triple: [Centauro II, sightingSystems, day/night sights]
-
A.
sightingSystem
chosen
Indicates a relationship where a system is used to detect, observe, or track targets or objects, typically for monitoring or aiming purposes.
-
B.
sightingState
Indicates the current status or condition of a reported sighting within its tracking or verification process.
-
C.
sightType
Indicates the specific kind or category of sight or visual perception associated with an entity or event.
-
D.
observationPlatform
Indicates that one entity serves as the physical or virtual platform, site, or facility from which observations of another entity or phenomenon are made.
-
E.
sightMounting
Indicates that an entity is equipped with or has a sighting device installed or mounted onto it.
- 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_69ca831d7b148190a6e32c1de43ab13b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5581d308190b47d76dd49a36529 |
completed | March 31, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69cbd107633c8190a36ba50e07876918 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:13 p.m.