Triple
T35027915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Market Street, Sydney |
E1010392
|
entity |
| Predicate | hasEndA |
P38695
|
FINISHED |
| Object | Sussex Street, Sydney |
—
|
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: Sussex Street, Sydney | Statement: [Market Street, Sydney, hasEndA, Sussex Street, Sydney]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndA Context triple: [Market Street, Sydney, hasEndA, Sussex Street, Sydney]
-
A.
hasEnd
chosen
Indicates that one entity serves as the terminal point, boundary, or conclusion of another entity or process.
-
B.
hasEnding
Indicates that one entity concludes with, or terminates in, another entity (such as a specific substring, segment, or final component).
-
C.
hasEndConstruction
Indicates that an entity is associated with, or terminates in, a specific construction or structural element at its end.
-
D.
canEndOn
Indicates that one entity is allowed or able to terminate, conclude, or finish with another specified entity or condition.
-
E.
hasCapitalAtEnd
Indicates that the capital or uppercase letter appears at the end of the given string or sequence.
- 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_69f76dccf0108190af43b465d3750196 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
Created at: May 3, 2026, 4:01 p.m.