Triple
T9091752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Clair County, Illinois |
E217903
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Lebanon, Illinois
Lebanon, Illinois is a small city in southwestern Illinois known for its historic downtown and as the home of McKendree University, the oldest college in the state.
|
E849099
|
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: Lebanon, Illinois | Statement: [St. Clair County, Illinois, contains, Lebanon, Illinois]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lebanon, Illinois Context triple: [St. Clair County, Illinois, contains, Lebanon, Illinois]
-
A.
LaPlace, Illinois
LaPlace, Illinois is a small rural village located in Piatt County in central Illinois.
-
B.
Morrison, Illinois
Morrison, Illinois is a small city in Whiteside County that serves as the county seat and lies within northwestern Illinois.
-
C.
Leland, Illinois
Leland, Illinois is a small rural village located in north-central Illinois within LaSalle County.
-
D.
Leonore, Illinois
Leonore, Illinois is a small village located in LaSalle County in north-central Illinois, United States.
-
E.
Kenilworth, Illinois
Kenilworth, Illinois is a small, affluent North Shore suburb of Chicago known for its planned residential character and high-quality schools.
- 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: Lebanon, Illinois Triple: [St. Clair County, Illinois, contains, Lebanon, Illinois]
Generated description
Lebanon, Illinois is a small city in southwestern Illinois known for its historic downtown and as the home of McKendree University, the oldest college in the state.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lebanon, Illinois Target entity description: Lebanon, Illinois is a small city in southwestern Illinois known for its historic downtown and as the home of McKendree University, the oldest college in the state.
-
A.
LaPlace, Illinois
LaPlace, Illinois is a small rural village located in Piatt County in central Illinois.
-
B.
Morrison, Illinois
Morrison, Illinois is a small city in Whiteside County that serves as the county seat and lies within northwestern Illinois.
-
C.
Leland, Illinois
Leland, Illinois is a small rural village located in north-central Illinois within LaSalle County.
-
D.
Leonore, Illinois
Leonore, Illinois is a small village located in LaSalle County in north-central Illinois, United States.
-
E.
Kenilworth, Illinois
Kenilworth, Illinois is a small, affluent North Shore suburb of Chicago known for its planned residential character and high-quality schools.
- 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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc96b18b24819097b525ddad3a85c0 |
completed | April 1, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d59af45f2881908516277f7f625131 |
completed | April 8, 2026, 12:01 a.m. |
| NEDg | Description generation | batch_69d59b92767481908c82ba1f804dcbe2 |
completed | April 8, 2026, 12:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d59c00773081909ac8ef13dc901bfc |
completed | April 8, 2026, 12:06 a.m. |
Created at: March 30, 2026, 7:14 p.m.