Triple
T25554790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collins Street, Melbourne |
E640539
|
entity |
| Predicate | westernEndCharacter |
P51120
|
FINISHED |
| Object | financial district |
—
|
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: financial district | Statement: [Collins Street, Melbourne, westernEndCharacter, financial district]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: westernEndCharacter Context triple: [Collins Street, Melbourne, westernEndCharacter, financial district]
-
A.
westEndProduction
Indicates that one entity is a theatrical production that was staged in London’s West End, associated with the other entity (such as a play, musical, or venue).
-
B.
originalWestEndRunEnd
Indicates the date or point in time when a production’s original run in London’s West End concluded.
-
C.
hasTerminusWest
chosen
Indicates that something has its western endpoint, terminus, or final stop at the referenced entity.
-
D.
westernTerminusNear
Indicates that the western endpoint of one entity is located close to another entity.
-
E.
terminusEast
Indicates that one entity serves as the eastern endpoint or final stop of another entity, such as a route, line, or path.
- 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_69e75dc101a881909fd33b02174e9768 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8c8e1688190af8d9be4660c4888 |
completed | May 2, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 3:38 p.m.