Triple
T27324783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RAF Hemswell |
E689611
|
entity |
| Predicate | closureUse |
P162187
|
FINISHED |
| Object | industrial estate |
—
|
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: industrial estate | Statement: [RAF Hemswell, closureUse, industrial estate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closureUse Context triple: [RAF Hemswell, closureUse, industrial estate]
-
A.
closureUse
chosen
Indicates that one entity makes use of another entity within a closure, typically capturing it from an enclosing scope for later execution.
-
B.
closureBy
Indicates that one entity causes, performs, or is responsible for the closing or termination of another entity, event, or process.
-
C.
closure
Indicates that an entity is closed or not accessible/available for use, entry, or interaction.
-
D.
closureType
Indicates the specific manner or condition in which something is closed, completed, or terminated within a process or relationship.
-
E.
closureAffected
Indicates that an entity is impacted or influenced by the closing or termination of another entity, process, or resource.
- 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_69ef355d4cb08190ab032c0a2e7d3753 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627ed03ac8190a17ddacba96f8a48 |
completed | May 2, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:35 a.m.