Triple
T30392658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CANDU reactor technology |
E773129
|
entity |
| Predicate | fuelBundleType |
P169153
|
FINISHED |
| Object | short cylindrical fuel bundles |
—
|
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: short cylindrical fuel bundles | Statement: [CANDU reactor technology, fuelBundleType, short cylindrical fuel bundles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fuelBundleType Context triple: [CANDU reactor technology, fuelBundleType, short cylindrical fuel bundles]
-
A.
serviceBundleType
Indicates the classification or category of a service bundle that specifies what kind of grouped services it represents.
-
B.
cargoForm
Indicates that one entity serves as the physical or structural form in which another entity’s cargo or contents are contained or transported.
-
C.
fuseType
Indicates the specific kind or category of fuse associated with or used in relation to an entity.
-
D.
fareProductType
Indicates the specific category or type of fare product associated with a ticket, booking, or travel transaction.
-
E.
bundle
Indicates that multiple items are grouped or packaged together as a single combined unit or offering.
- F. None of above. chosen
Provenance (4 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_69f2248ef0a48190aa54d4d8ac3e5758 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f685a6ddb08190a4664c0597e80bf2 |
completed | May 2, 2026, 11:15 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f679496c188190ba585792f987a1f4 |
completed | May 2, 2026, 10:23 p.m. |
Created at: April 29, 2026, 8:02 p.m.