Triple
T434041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penobscot County, Maine |
E9773
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object |
Dexter, Maine
Dexter, Maine is a small New England town known for its historic mill industry and lakeside setting in central Maine.
|
E108488
|
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: Dexter, Maine | Statement: [Penobscot County, Maine, hasTown, Dexter, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dexter, Maine Context triple: [Penobscot County, Maine, hasTown, Dexter, Maine]
-
A.
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.
-
B.
Holden, Maine
Holden, Maine is a small New England town located near Bangor in eastern Maine, known for its rural character and scenic, wooded landscape.
-
C.
Phillips, Maine
Phillips, Maine is a small rural town in western Maine known for its historic narrow-gauge railroad heritage and scenic mountain surroundings.
-
D.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
E.
Temple, Maine
Temple, Maine is a small rural town in western Maine known for its forested landscape and quiet, close-knit community.
- 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: Dexter, Maine Triple: [Penobscot County, Maine, hasTown, Dexter, Maine]
Generated description
Dexter, Maine is a small New England town known for its historic mill industry and lakeside setting in central Maine.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dexter, Maine Target entity description: Dexter, Maine is a small New England town known for its historic mill industry and lakeside setting in central Maine.
-
A.
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.
-
B.
Holden, Maine
Holden, Maine is a small New England town located near Bangor in eastern Maine, known for its rural character and scenic, wooded landscape.
-
C.
Phillips, Maine
Phillips, Maine is a small rural town in western Maine known for its historic narrow-gauge railroad heritage and scenic mountain surroundings.
-
D.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
E.
Temple, Maine
Temple, Maine is a small rural town in western Maine known for its forested landscape and quiet, close-knit community.
- 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_69a2e801e1d48190b505d1dd336b52ac |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ef0a008c8190ae0aa25e4df9c35f |
completed | Feb. 28, 2026, 1:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7cf473e48819095390a5904429a9c |
completed | March 4, 2026, 6:20 a.m. |
| NEDg | Description generation | batch_69a7d063fe8c81909a32afaf2798297f |
completed | March 4, 2026, 6:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a7d0c6a14c81909d98c648aef4e87b |
completed | March 4, 2026, 6:27 a.m. |
Created at: Feb. 28, 2026, 1:11 p.m.