Triple
T28382198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Litvinenko inquiry in the United Kingdom |
E718916
|
entity |
| Predicate | chairOccupation |
P164446
|
FINISHED |
| Object | High Court judge |
—
|
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: High Court judge | Statement: [Litvinenko inquiry in the United Kingdom, chairOccupation, High Court judge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chairOccupation Context triple: [Litvinenko inquiry in the United Kingdom, chairOccupation, High Court judge]
-
A.
chairHolderStatus
Indicates the status or condition of an entity in relation to holding a specific chair or official position.
-
B.
seatSince
Indicates that an entity has held a particular seat, position, or place continuously since a specified point in time.
-
C.
seatIs
Indicates that one entity functions as the seat or seating position of another entity.
-
D.
capacityPerChair
Indicates the amount of capacity (such as weight, volume, or occupancy) that is assigned to or supported by each individual chair.
-
E.
seatOwnedBy
Indicates that a particular seat is possessed or held in ownership by a specific entity.
- 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_69eff6ef211081909d31d9be5f5567e6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64cb6c8708190b0a947d7da770920 |
completed | May 2, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
| PDg | Predicate description generation | batch_69f64bca8574819095e081cbb7e2f369 |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 28, 2026, 1:07 a.m.