Triple
T19539817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tensas River |
E488866
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Franklin Parish |
—
|
NE NERFINISHED |
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: Franklin Parish | Statement: [Tensas River, locatedIn, Franklin Parish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Franklin Parish Context triple: [Tensas River, locatedIn, Franklin Parish]
-
A.
Franklin Parish
chosen
Franklin Parish is a rural parish in northeastern Louisiana known for its agriculture-based economy and small-town communities.
-
B.
Madison Parish
Madison Parish is a rural parish in northeastern Louisiana known for its agricultural economy and location along the Mississippi River.
-
C.
Lincoln Parish
Lincoln Parish is a north-central Louisiana parish known for its seat in Ruston and as home to Louisiana Tech University.
-
D.
Renard Parish
Renard Parish is a fictional Louisiana parish that serves as the broader setting for the supernatural events surrounding the town of Bon Temps in the TV series "True Blood."
-
E.
Vermilion Parish
Vermilion Parish is a coastal parish in southern Louisiana known for its Cajun culture, agriculture, and wetlands along the Gulf of Mexico.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63871d00881909ed7371ae5577957 |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.