Triple
T16357631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GRACES |
E397222
|
entity |
| Predicate | feedsInstrumentThrough |
P83374
|
FINISHED |
| Object | long optical fiber link between Gemini North and CFHT |
—
|
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: long optical fiber link between Gemini North and CFHT | Statement: [GRACES, feedsInstrumentThrough, long optical fiber link between Gemini North and CFHT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feedsInstrumentThrough Context triple: [GRACES, feedsInstrumentThrough, long optical fiber link between Gemini North and CFHT]
-
A.
feedDevice
chosen
Indicates that one entity supplies or provides input, material, or data to a device for its operation or processing.
-
B.
feedsAccelerator
Indicates that one entity supplies or directs input, resources, or power into an accelerator system for its operation.
-
C.
linkedInstrument
Indicates that one entity is associated with or connected to another as a related or corresponding instrument.
-
D.
providesInstrument
Indicates that one entity supplies or makes available an instrument or tool for another entity’s use.
-
E.
feedsOn
Indicates that one entity obtains nourishment by consuming another entity as food.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2fad0b1948190a66ec7d2a310cc83 |
completed | April 18, 2026, 3:30 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.