Triple
T4366959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saco River |
E98798
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Standish, Maine |
E445065
|
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: Standish, Maine | Statement: [Saco River, passesThrough, Standish, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Standish, Maine Context triple: [Saco River, passesThrough, Standish, Maine]
-
A.
Standish, Maine
chosen
Standish, Maine is a small town in southern Maine known for its rural character, lakeside recreation on Sebago Lake, and proximity to the Portland metropolitan area.
-
B.
Dixfield, Maine
Dixfield, Maine is a small New England town in western Maine known for its rural character and location along the Androscoggin River in Oxford County.
-
C.
Addison, Maine
Addison, Maine is a small coastal town in Washington County known for its fishing heritage and scenic Downeast shoreline.
-
D.
Greenfield, Maine
Greenfield, Maine is a small rural town located in Penobscot County in the central part of the state.
-
E.
Howland, Maine
Howland, Maine is a small rural town in Penobscot County known for its location along the Penobscot and Piscataquis Rivers and its outdoor recreation opportunities.
- 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_69e5b744b534819095b272ba8943f7b7 |
completed | April 20, 2026, 5:19 a.m. |
Created at: March 12, 2026, 11:17 p.m.