Triple
T2388872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Maine |
E48893
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Gray, Maine |
E445354
|
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: Gray, Maine | Statement: [Southern Maine, contains, Gray, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gray, Maine Context triple: [Southern Maine, contains, Gray, Maine]
-
A.
Gray, Maine
chosen
Gray, Maine is a small New England town in southern Maine known for its rural character, proximity to Portland, and the Maine Wildlife Park.
-
B.
Warren, Maine
Warren, Maine is a small town in Knox County known for its rural character and location along the St. George River in midcoast Maine.
-
C.
Rockland, Maine
Rockland, Maine is a coastal city in midcoast Maine known for its busy harbor, maritime industries, and role as a transportation and cultural hub for the region.
-
D.
Greene, Maine
Greene, Maine is a small rural town in Androscoggin County known for its quiet residential character and proximity to the Lewiston–Auburn area.
-
E.
Porter, Maine
Porter, Maine is a small rural town in Oxford County known for its scenic setting near the New Hampshire border and its traditional New England character.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7dca9248190b634ae9e02f6899a |
completed | March 7, 2026, 6:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c870539eb08190936adcfbab395654 |
completed | March 29, 2026, 12:20 a.m. |
Created at: March 4, 2026, 7:57 p.m.