Triple
T12430045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City of Broken Hill |
E297001
|
entity |
| Predicate | isInOutback |
P104887
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [City of Broken Hill, isInOutback, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInOutback Context triple: [City of Broken Hill, isInOutback, true]
-
A.
isBehind
Indicates that one entity is positioned to the rear of another entity along a relevant spatial or directional axis.
-
B.
isAt
Indicates that one entity is located at or present in the place or position of another entity.
-
C.
isOutAndBack
Indicates that an action, route, or movement involves going from a starting point to a destination and then returning along the same path back to the starting point.
-
D.
isInCabinet
Indicates that one entity serves as a member of the governing cabinet associated with another entity (such as a government or administration).
-
E.
isForecourtOf
Indicates that one place or area serves as the forecourt (an open, typically frontal space or entrance area) of another place or structure.
- F. None of above. chosen
Provenance (4 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
| PDg | Predicate description generation | batch_69d94df652cc8190a1d2d685fa87cf98 |
completed | April 10, 2026, 7:22 p.m. |
Created at: April 8, 2026, 9:55 p.m.