Triple
T5335535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Bend, Indiana |
E123815
|
entity |
| Predicate | hasPark |
P105
|
FINISHED |
| Object |
Potawatomi Park
Potawatomi Park is a popular public park in South Bend, Indiana, known for its zoo, playgrounds, and recreational facilities.
|
E512942
|
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: Potawatomi Park | Statement: [South Bend, Indiana, hasPark, Potawatomi Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Potawatomi Park Context triple: [South Bend, Indiana, hasPark, Potawatomi Park]
-
A.
Vilas Park
Vilas Park is a popular lakeside public park in Madison, Wisconsin, known for its recreational facilities, zoo, and scenic shoreline along Lake Wingra.
-
B.
Manito Park
Manito Park is a historic public park in Spokane, Washington, known for its formal gardens, conservatory, and scenic walking paths.
-
C.
Kellogg Park
Kellogg Park is a central public gathering space and community park located in downtown Plymouth, Michigan.
-
D.
Marquette Park
Marquette Park is a historic lakeside public park in Gary, Indiana, known for its beaches, dunes, and recreational facilities along Lake Michigan.
-
E.
Marquette Park
Marquette Park is a large historic public park on Chicago’s Southwest Side, known for its lagoon, recreational facilities, and role in the city’s civil rights history.
- 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: Potawatomi Park Triple: [South Bend, Indiana, hasPark, Potawatomi Park]
Generated description
Potawatomi Park is a popular public park in South Bend, Indiana, known for its zoo, playgrounds, and recreational facilities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Potawatomi Park Target entity description: Potawatomi Park is a popular public park in South Bend, Indiana, known for its zoo, playgrounds, and recreational facilities.
-
A.
Vilas Park
Vilas Park is a popular lakeside public park in Madison, Wisconsin, known for its recreational facilities, zoo, and scenic shoreline along Lake Wingra.
-
B.
Manito Park
Manito Park is a historic public park in Spokane, Washington, known for its formal gardens, conservatory, and scenic walking paths.
-
C.
Kellogg Park
Kellogg Park is a central public gathering space and community park located in downtown Plymouth, Michigan.
-
D.
Marquette Park
Marquette Park is a historic lakeside public park in Gary, Indiana, known for its beaches, dunes, and recreational facilities along Lake Michigan.
-
E.
Marquette Park
Marquette Park is a large historic public park on Chicago’s Southwest Side, known for its lagoon, recreational facilities, and role in the city’s civil rights history.
- 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85af799081909ee60bfbb65149ee |
completed | March 20, 2026, 5:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf18be4bb88190a2b83e51716e677e |
completed | March 21, 2026, 10:16 p.m. |
| NEDg | Description generation | batch_69bf194c53a48190b0895bbe9aa2f6f1 |
completed | March 21, 2026, 10:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf1a198418819089b25102733f9191 |
completed | March 21, 2026, 10:22 p.m. |
Created at: March 20, 2026, 2 p.m.