Triple
T2136912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo Bridge |
E46673
|
entity |
| Predicate | isMajorCrossingIn |
P12328
|
FINISHED |
| Object | central London |
—
|
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: central London | Statement: [Waterloo Bridge, isMajorCrossingIn, central London]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isMajorCrossingIn Context triple: [Waterloo Bridge, isMajorCrossingIn, central London]
-
A.
hasMajorCrossing
chosen
Indicates that one entity has a significant or primary intersection or crossing with another entity.
-
B.
isMajorInterchangeFor
Indicates that one location functions as a primary hub where multiple routes or lines connect or transfer between each other for another location.
-
C.
isLocalCrossroads
Indicates that a location serves as a junction where multiple local routes or streets intersect.
-
D.
isMajorRoadIn
Indicates that a road is classified as a major road within a specified geographic area or jurisdiction.
-
E.
isMajorAccessPointFor
Indicates that something serves as a primary or significant entry or connection point for accessing another entity or system.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbf74147c81908793c3694894f94a |
completed | March 7, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69abbd96a3b0819081efbfef975e1513 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.