Triple
T18306920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knox County, Indiana |
E438509
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object |
Oaktown, Indiana
Oaktown, Indiana is a small rural town located in southwestern Indiana within Knox County.
|
E1338098
|
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: Oaktown, Indiana | Statement: [Knox County, Indiana, containsTown, Oaktown, Indiana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oaktown, Indiana Context triple: [Knox County, Indiana, containsTown, Oaktown, Indiana]
-
A.
Oakland City, Indiana
Oakland City, Indiana is a small city in Gibson County known for being home to Oakland City University and serving as a local educational and agricultural hub in southwestern Indiana.
-
B.
Rochester, Indiana
Rochester, Indiana is a small city in Fulton County that serves as the county seat and a local hub for the surrounding rural region in northern Indiana.
-
C.
Elwood, Indiana
Elwood, Indiana is a small Midwestern city best known as the birthplace of 1940 Republican presidential nominee Wendell Willkie.
-
D.
Fairmount, Indiana
Fairmount, Indiana is a small Midwestern town best known as the childhood home and burial place of actor James Dean.
-
E.
Brownsville, Indiana
Brownsville, Indiana is a small unincorporated community located in rural Union County in the eastern part of the state.
- 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: Oaktown, Indiana Triple: [Knox County, Indiana, containsTown, Oaktown, Indiana]
Generated description
Oaktown, Indiana is a small rural town located in southwestern Indiana within Knox County.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Oaktown, Indiana Target entity description: Oaktown, Indiana is a small rural town located in southwestern Indiana within Knox County.
-
A.
Oakland City, Indiana
Oakland City, Indiana is a small city in Gibson County known for being home to Oakland City University and serving as a local educational and agricultural hub in southwestern Indiana.
-
B.
Rochester, Indiana
Rochester, Indiana is a small city in Fulton County that serves as the county seat and a local hub for the surrounding rural region in northern Indiana.
-
C.
Elwood, Indiana
Elwood, Indiana is a small Midwestern city best known as the birthplace of 1940 Republican presidential nominee Wendell Willkie.
-
D.
Fairmount, Indiana
Fairmount, Indiana is a small Midwestern town best known as the childhood home and burial place of actor James Dean.
-
E.
Brownsville, Indiana
Brownsville, Indiana is a small unincorporated community located in rural Union County in the eastern part of the state.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021519a481908a9b6561946f1c65 |
completed | April 19, 2026, 4:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a052b1f07f48190af45cce468a037b7 |
completed | May 14, 2026, 1:53 a.m. |
| NEDg | Description generation | batch_6a052be41ec88190a6b2ae87c3e42150 |
completed | May 14, 2026, 1:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a052c3488f881909e35ec51612cad6f |
completed | May 14, 2026, 1:58 a.m. |
Created at: April 10, 2026, 10:35 a.m.