Triple
T21035029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ballarat |
E518165
|
entity |
| Predicate | rankInVictoriaByPopulation |
P59028
|
FINISHED |
| Object | third-largest city |
—
|
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: third-largest city | Statement: [Ballarat, rankInVictoriaByPopulation, third-largest city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankInVictoriaByPopulation Context triple: [Ballarat, rankInVictoriaByPopulation, third-largest city]
-
A.
populationRankInVictoria
chosen
Indicates the relative position of an entity in an ordered ranking based on its population size within the region of Victoria.
-
B.
capitalCityPopulationRankInAustralia
Indicates the relative population rank of a capital city compared to other capital cities within Australia.
-
C.
rankInSouthAustraliaByPopulation
Indicates the position of an entity in an ordered list of South Australian entities sorted by their population size.
-
D.
populationRankInQueensland
Indicates the relative position of an entity in terms of population size compared to other entities within Queensland.
-
E.
hasPopulationRankInTasmania
Indicates the relative position of an entity in the ordered list of population sizes within Tasmania.
- 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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc858d808190a8489aac801a4f51 |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf6728881908a2a43a5c8804a2a |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:01 p.m.