Triple
T15321665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sturt County |
E366305
|
entity |
| Predicate | hasNeighbour |
P5707
|
FINISHED |
| Object |
Hume County
Hume County is a cadastral division in New South Wales, Australia, used for land administration and property identification.
|
E1180129
|
NE FINISHED |
How this triple was built (4 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: Hume County | Statement: [Sturt County, hasNeighbour, Hume County]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hume County Context triple: [Sturt County, hasNeighbour, Hume County]
-
A.
Harrison County
Harrison County is an East Texas county in the United States, historically significant for its role in the antebellum South and centered around its county seat, Marshall.
-
B.
Harrison County
Harrison County is a rural county in western Iowa known for its agricultural landscape, small communities, and location along the Missouri River.
-
C.
Harrison County
Harrison County is a coastal county in southern Mississippi known for its tourism, casinos, and the cities of Biloxi and Gulfport.
-
D.
Turner County
Turner County is a rural county in southeastern South Dakota that forms part of the Sioux Falls metropolitan region.
-
E.
Clay County
Clay County is the fictional Georgia county that serves as the setting for the Twelve Oaks plantation in Margaret Mitchell’s novel "Gone with the Wind."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hume County Triple: [Sturt County, hasNeighbour, Hume County]
Generated description
Hume County is a cadastral division in New South Wales, Australia, used for land administration and property identification.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hume County Target entity description: Hume County is a cadastral division in New South Wales, Australia, used for land administration and property identification.
-
A.
Harrison County
Harrison County is an East Texas county in the United States, historically significant for its role in the antebellum South and centered around its county seat, Marshall.
-
B.
Harrison County
Harrison County is a rural county in western Iowa known for its agricultural landscape, small communities, and location along the Missouri River.
-
C.
Harrison County
Harrison County is a coastal county in southern Mississippi known for its tourism, casinos, and the cities of Biloxi and Gulfport.
-
D.
Turner County
Turner County is a rural county in southeastern South Dakota that forms part of the Sioux Falls metropolitan region.
-
E.
Clay County
Clay County is the fictional Georgia county that serves as the setting for the Twelve Oaks plantation in Margaret Mitchell’s novel "Gone with the Wind."
- F. None of above. chosen
Provenance (5 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd460288190b5c41f0a0aeee949 |
completed | April 16, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa11f77788190866e0820d33af588 |
completed | May 9, 2026, 9:03 p.m. |
| NEDg | Description generation | batch_69ffa417ee248190808b0fecfb58d705 |
completed | May 9, 2026, 9:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffa5372f248190827cdc4985fee1ef |
completed | May 9, 2026, 9:20 p.m. |
Created at: April 10, 2026, 3:16 a.m.