Triple
T248593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Society University Research Fellowships |
E5091
|
entity |
| Predicate | typicalHost |
P2592
|
FINISHED |
| Object | UK university department |
—
|
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: UK university department | Statement: [Royal Society University Research Fellowships, typicalHost, UK university department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalHost Context triple: [Royal Society University Research Fellowships, typicalHost, UK university department]
-
A.
host
chosen
Indicates that one entity provides space, resources, or services to accommodate, receive, or entertain another entity.
-
B.
typicalDeployment
Indicates that one entity represents the standard or most commonly used deployment configuration or pattern for the other entity.
-
C.
typicalEngine
Indicates that an entity is the standard or commonly used engine for another entity (such as a vehicle, device, or system).
-
D.
typicalKey
Indicates that the referenced key is the standard or most commonly used key associated with an entity or context.
-
E.
hosted
Indicates that one entity organized and provided the venue or platform for an event, activity, or presence involving 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_69a257c4bf688190a46ebbf411ab7473 |
completed | Feb. 28, 2026, 2:49 a.m. |
| NER | Named-entity recognition | batch_69a25d154ebc819087a5c9dc4f62ff44 |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b64ea3081908de626a0e1445bdb |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:54 a.m.