Triple
T32537696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Capitals Limited |
E831632
|
entity |
| Predicate | connectedCities |
P85182
|
FINISHED |
| Object | London |
—
|
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: London | Statement: [The Capitals Limited, connectedCities, London]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectedCities Context triple: [The Capitals Limited, connectedCities, London]
-
A.
capitalCityConnected
Indicates that there is a transportation or infrastructural link between a capital city and another location.
-
B.
cityRelationship
chosen
Indicates a relationship that specifies how one city is connected or related to another city (e.g., administratively, geographically, or functionally).
-
C.
linkedCity
Indicates that two entities are associated with each other through a specific city, such as being located in, connected via, or related by that city.
-
D.
isNeighboringCityOf
Indicates that one city is geographically adjacent to or directly borders another city.
-
E.
betweenCities
Indicates a relationship where something is located or occurs in the space or context separating two specified cities.
- 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_69f34924b1cc8190ad3aca0c0f012a7e |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fedfd913f48190bdcd450980868d9a |
completed | May 9, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fedf58c6e88190821a7156054c9086 |
completed | May 9, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:01 a.m.