Triple
T25979779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sagnac interferometer |
E646034
|
entity |
| Predicate | canUseMedium |
P9928
|
FINISHED |
| Object | free‑space path |
—
|
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: free‑space path | Statement: [Sagnac interferometer, canUseMedium, free‑space path]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canUseMedium Context triple: [Sagnac interferometer, canUseMedium, free‑space path]
-
A.
usedMedium
Indicates that an action or communication was carried out through a particular medium or channel.
-
B.
canUse
chosen
Indicates that one entity has the ability, permission, or suitability to make use of another entity or resource.
-
C.
usesActiveMedium
Indicates that an entity performs an action or operates by employing an active medium as the means or channel for that action or process.
-
D.
canBeUsed
Indicates that one entity is suitable or available to serve a particular function, purpose, or role in relation to another entity or context.
-
E.
isFromMedium
Indicates that something originates from, is derived from, or was obtained via a particular medium or channel.
- 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6050e507881909e3bc0c33e8a8c7e |
completed | May 2, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:54 a.m.