Triple
T5099115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hooke's law |
E114938
|
entity |
| Predicate | validWithin |
P9768
|
FINISHED |
| Object | elastic limit |
—
|
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: elastic limit | Statement: [Hooke's law, validWithin, elastic limit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: validWithin Context triple: [Hooke's law, validWithin, elastic limit]
-
A.
validIn
chosen
Indicates that a given entity, statement, or condition is applicable, correct, or legally/semantically acceptable within a specified context, scope, or domain.
-
B.
timePeriodWithin
Indicates that one time period is entirely contained within the bounds of another time period.
-
C.
validityType
Indicates the specific kind or category of validity that characterizes how or under what conditions something is considered valid.
-
D.
maintainedWithin
Indicates that one entity is kept, preserved, or sustained inside the boundaries or context of another entity.
-
E.
existsWithin
Indicates that one entity is located inside the spatial, temporal, or conceptual boundaries of another entity.
- 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_69bd443fc49c819089629c00e311310c |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7568e9c881909f114973faef6832 |
completed | March 20, 2026, 4:27 p.m. |
| PD | Predicate disambiguation | batch_69bd715e06808190931934dc9930f997 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.