Triple
T9937983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | photon |
E194003
|
entity |
| Predicate | propagatesAt |
P58682
|
FINISHED |
| Object | speed of light in vacuum |
—
|
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: speed of light in vacuum | Statement: [photon, propagatesAt, speed of light in vacuum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: propagatesAt Context triple: [photon, propagatesAt, speed of light in vacuum]
-
A.
propagateAt
chosen
Indicates that an effect, signal, or influence spreads or is transmitted to a specific location, time, or context.
-
B.
propagateAlong
Indicates that something (such as an effect, signal, or influence) spreads or is transmitted along a specified path, medium, or connection.
-
C.
propagationMethod
Indicates the means or mechanism by which something spreads, reproduces, or is transmitted from one entity or location to another.
-
D.
propagatorType
Indicates the specific method or model used to propagate or advance a state (such as position, condition, or effect) from one point in time or space to another.
-
E.
propagationMedium
Indicates the medium or substance through which something (such as a signal, wave, or influence) is transmitted or propagated.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e64760819094f599f158d32f33 |
completed | April 2, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9428cc81909b4b4938566d78a7 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:44 p.m.