Triple
T3509191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington County, Maine |
E74153
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Addison, Maine
Addison, Maine is a small coastal town in Washington County known for its fishing heritage and scenic Downeast shoreline.
|
E848327
|
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: Addison, Maine | Statement: [Washington County, Maine, contains, Addison, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Addison, Maine Context triple: [Washington County, Maine, contains, Addison, Maine]
-
A.
Blaine, Maine
Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
-
B.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
C.
Winslow, Maine
Winslow, Maine is a small town in Kennebec County known for its rural character, historic sites, and location along the Kennebec River in central Maine.
-
D.
Greenfield, Maine
Greenfield, Maine is a small rural town located in Penobscot County in the central part of the state.
-
E.
Van Buren, Maine
Van Buren, Maine is a small town in northern Maine along the Saint John River, directly across from New Brunswick, Canada, known for its French-Acadian heritage and rural character.
- 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: Addison, Maine Triple: [Washington County, Maine, contains, Addison, Maine]
Generated description
Addison, Maine is a small coastal town in Washington County known for its fishing heritage and scenic Downeast shoreline.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Addison, Maine Target entity description: Addison, Maine is a small coastal town in Washington County known for its fishing heritage and scenic Downeast shoreline.
-
A.
Blaine, Maine
Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
-
B.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
C.
Winslow, Maine
Winslow, Maine is a small town in Kennebec County known for its rural character, historic sites, and location along the Kennebec River in central Maine.
-
D.
Greenfield, Maine
Greenfield, Maine is a small rural town located in Penobscot County in the central part of the state.
-
E.
Van Buren, Maine
Van Buren, Maine is a small town in northern Maine along the Saint John River, directly across from New Brunswick, Canada, known for its French-Acadian heritage and rural character.
- 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc0cc394819087a9b598023f4f93 |
completed | March 8, 2026, 6:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3549788608190a1949eb254e43a8e |
completed | April 6, 2026, 6:37 a.m. |
| NEDg | Description generation | batch_69d356211fd8819089db018473b959e9 |
completed | April 6, 2026, 6:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d356a1c48c81909820ad66d96c9cc5 |
completed | April 6, 2026, 6:45 a.m. |
Created at: March 8, 2026, 3:18 p.m.