Triple
T10908740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | F-2 |
E257636
|
entity |
| Predicate | relativeToF3 |
P25304
|
FINISHED |
| Object | lighter-duty than F-3 |
—
|
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: lighter-duty than F-3 | Statement: [F-2, relativeToF3, lighter-duty than F-3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeToF3 Context triple: [F-2, relativeToF3, lighter-duty than F-3]
-
A.
relativePosition
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
-
B.
relativePositionInSystem
Indicates the spatial or ordered position an entity occupies within a larger system or structured arrangement.
-
C.
relativeLevel
chosen
Indicates a comparative relationship specifying how one entity’s level, degree, or intensity of some property stands relative to that of another entity.
-
D.
movesRelativeTo
Indicates that one entity changes its position or orientation with respect to another entity, rather than with respect to a fixed reference frame.
-
E.
relativeMotionType
Indicates the type or nature of motion occurring between two entities relative to one another.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7706824d08190ba894d144cc6b3ba |
completed | April 9, 2026, 9:24 a.m. |
| PD | Predicate disambiguation | batch_69d70d3d69e08190bb369e9a7927142c |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:22 p.m.