Triple
T35790788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FLIR1 |
E1034685
|
entity |
| Predicate | hasFrameOverlay |
P164909
|
FINISHED |
| Object | sensor telemetry data |
—
|
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: sensor telemetry data | Statement: [FLIR1, hasFrameOverlay, sensor telemetry data]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFrameOverlay Context triple: [FLIR1, hasFrameOverlay, sensor telemetry data]
-
A.
hasFrameEffect
Indicates that one entity produces or is associated with a visual or stylistic frame-related effect on another entity.
-
B.
hasFrameElement
Indicates that a frame (or structured conceptual scenario) includes or is associated with a specific frame element (a participant, role, or component within that frame).
-
C.
hasFrameType
Indicates that an entity possesses or is associated with a specific type or category of frame.
-
D.
isLayeredOver
chosen
Indicates that one entity is positioned or arranged directly on top of another, partially or fully covering it in a layered manner.
-
E.
hasFrameFinish
Indicates that an entity’s frame possesses a specific surface treatment or finish.
- 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_69f76e1575908190aaa306d843b41c14 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:06 p.m.