Triple
T31884487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windscale fire |
E813969
|
entity |
| Predicate | reactorName |
P744
|
FINISHED |
| Object |
Windscale Pile 1
Windscale Pile 1 was a British early graphite-moderated, air-cooled nuclear reactor at the Windscale site in Cumbria, best known as the location of the 1957 Windscale fire, one of the worst nuclear accidents in UK history.
|
E1982483
|
NE FINISHED |
How this triple was built (3 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: Windscale Pile 1 | Statement: [Windscale fire, reactorName, Windscale Pile 1]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Windscale Pile 1 Triple: [Windscale fire, reactorName, Windscale Pile 1]
Generated description
Windscale Pile 1 was a British early graphite-moderated, air-cooled nuclear reactor at the Windscale site in Cumbria, best known as the location of the 1957 Windscale fire, one of the worst nuclear accidents in UK history.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactorName Context triple: [Windscale fire, reactorName, Windscale Pile 1]
-
A.
runtimeName
Indicates the name of the runtime environment or platform under which an entity (such as a program or process) is executed.
-
B.
daemonName
Indicates the name assigned to a daemon process in a system.
-
C.
circuitName
Indicates that a specific name or label is assigned to a given circuit.
-
D.
boosterName
Indicates the name or designation assigned to a booster component associated with an entity or event.
-
E.
nameOf
chosen
Indicates that one entity is the name or designation of another entity.
- F. None of above.
Provenance (6 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6bbbef7a88190b0affdec1d41c1e0 |
completed | May 3, 2026, 3:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2e7fe591bc819098ecfe852e88149e |
completed | June 14, 2026, 10:18 a.m. |
| NEDg | Description generation | batch_6a2e80bfc09c81908b0f21d5dc3629e9 |
completed | June 14, 2026, 10:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2e81c63b8081909989e5e18ce19954 |
completed | June 14, 2026, 10:26 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: April 30, 2026, 11:57 p.m.