Triple
T24576578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North London Business Park |
E608125
|
entity |
| Predicate | hasBuildingUseClass |
P147436
|
FINISHED |
| Object | office (B1/B2 equivalent) |
—
|
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: office (B1/B2 equivalent) | Statement: [North London Business Park, hasBuildingUseClass, office (B1/B2 equivalent)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuildingUseClass Context triple: [North London Business Park, hasBuildingUseClass, office (B1/B2 equivalent)]
-
A.
hasBuildingClass
Indicates that a building is categorized as belonging to a specific building class or type.
-
B.
currentBuildingUse
chosen
Indicates the present functional purpose or activity for which a building is being used.
-
C.
containsBuildingType
Indicates that a location or area includes at least one building of the specified type.
-
D.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
-
E.
appliedToBuildingType
Indicates that something (such as a rule, measure, or classification) is specifically applicable to a particular type of building.
- 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_69e2c4cdab6c8190aae6e5d3de55c95e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9295ab08190b6c137c99bcd958f |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:29 a.m.