Triple
T4366964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saco River |
E98798
|
entity |
| Predicate | formsBorderBetween |
P224
|
FINISHED |
| Object | Saco, Maine |
E353308
|
NE FINISHED |
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: Saco, Maine | Statement: [Saco River, formsBorderBetween, Saco, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saco, Maine Context triple: [Saco River, formsBorderBetween, Saco, Maine]
-
A.
Saco, Maine
chosen
Saco, Maine is a small coastal city in southern Maine known for its historic mill district, beaches, and proximity to the Portland metropolitan area.
-
B.
Sanford, Maine
Sanford, Maine is a city in York County known for its historic textile mill heritage and its location in southern Maine near the New Hampshire border.
-
C.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
D.
Fairfield, Maine
Fairfield, Maine is a small town in Somerset County known for its rural character, proximity to the Kennebec River, and role as part of the greater Waterville area in central Maine.
-
E.
Addison, Maine
Addison, Maine is a small coastal town in Washington County known for its fishing heritage and scenic Downeast shoreline.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69b3454db3708190aeafd814413c4c3d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35201be7081908808e81634060f95 |
completed | March 12, 2026, 11:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6847ad9fc819085b0d6c886488c3b |
completed | April 20, 2026, 7:54 p.m. |
Created at: March 12, 2026, 11:17 p.m.