Triple
T35723109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl's Court Development Company |
E1032535
|
entity |
| Predicate | projectBorough |
P184652
|
FINISHED |
| Object | Royal Borough of Kensington and Chelsea |
—
|
NE NERFINISHED |
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: Royal Borough of Kensington and Chelsea | Statement: [Earl's Court Development Company, projectBorough, Royal Borough of Kensington and Chelsea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: projectBorough Context triple: [Earl's Court Development Company, projectBorough, Royal Borough of Kensington and Chelsea]
-
A.
primaryBorough
Indicates that one borough is the main or most significant borough associated with a given entity.
-
B.
positionInBorough
Indicates that one entity is located within or belongs to the geographic area of a specific borough.
-
C.
cityCouncilBorough
Indicates that a city council has jurisdiction over, or is associated with, a specific borough within the city.
-
D.
hasBoroughEndpoint
Indicates that something has an endpoint located within a specific borough.
-
E.
stationBorough
Indicates the borough or administrative district in which a station is located.
- 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_69f76e102b5881909e5d63a30a5cecbe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b365288c8190bcb11fcfba028737 |
completed | May 3, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
| PDg | Predicate description generation | batch_69f7b2f2b9ac8190aa05b8a1aa18ec2d |
completed | May 3, 2026, 8:41 p.m. |
Created at: May 3, 2026, 4:05 p.m.