Triple
T35859867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tayside Police |
E1036915
|
entity |
| Predicate | hadControlRoom |
P5521
|
FINISHED |
| Object | Dundee control room |
—
|
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: Dundee control room | Statement: [Tayside Police, hadControlRoom, Dundee control room]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadControlRoom Context triple: [Tayside Police, hadControlRoom, Dundee control room]
-
A.
hasRoom
chosen
Indicates that an entity possesses, contains, or is associated with a specific room.
-
B.
hasControlCab
Indicates that an entity is equipped with or includes a control cab used for operating or controlling it.
-
C.
controlRoomFeature
Indicates that a feature, element, or characteristic is part of, present in, or associated with a control room.
-
D.
hasProjectionRoom
Indicates that one entity (typically a venue or building) contains or is equipped with a projection room used for displaying films or visual media.
-
E.
hasHadPartyControl
Indicates that a political party has at some time held governing or majority control over a specified body, office, or jurisdiction.
- 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_69f76e1d279c8190843e5b64a0a12c3f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3883d48190b05e3d2da7a017ae |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.