Triple
T536576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aroostook County, Maine |
E12339
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object |
Masardis, Maine
Masardis, Maine is a small rural town in northern Maine known for its forested landscape and outdoor recreation opportunities.
|
E263849
|
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: Masardis, Maine | Statement: [Aroostook County, Maine, hasTown, Masardis, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Masardis, Maine Context triple: [Aroostook County, Maine, hasTown, Masardis, Maine]
-
A.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
B.
Veazie, Maine
Veazie, Maine is a small residential town in eastern Maine located along the Penobscot River near the city of Bangor.
-
C.
Blaine, Maine
Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
-
D.
Frenchville, Maine
Frenchville, Maine is a small, predominantly French-speaking town in northern Maine located along the Saint John River near the Canadian border.
-
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. 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: Masardis, Maine Triple: [Aroostook County, Maine, hasTown, Masardis, Maine]
Generated description
Masardis, Maine is a small rural town in northern Maine known for its forested landscape and outdoor recreation opportunities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Masardis, Maine Target entity description: Masardis, Maine is a small rural town in northern Maine known for its forested landscape and outdoor recreation opportunities.
-
A.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
B.
Veazie, Maine
Veazie, Maine is a small residential town in eastern Maine located along the Penobscot River near the city of Bangor.
-
C.
Blaine, Maine
chosen
Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
-
D.
Frenchville, Maine
Frenchville, Maine is a small, predominantly French-speaking town in northern Maine located along the Saint John River near the Canadian border.
-
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.
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_69a4933208e88190891f5debab1b776d |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a496da8e108190b4874c3b85290464 |
completed | March 1, 2026, 7:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af989077b881909eb04ffb1e252e8c |
completed | March 10, 2026, 4:05 a.m. |
| NEDg | Description generation | batch_69af99d25a1c81908061ebf996e4f470 |
completed | March 10, 2026, 4:10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69af9a94473c8190b97cedd374d9b032 |
completed | March 10, 2026, 4:14 a.m. |
Created at: March 1, 2026, 7:32 p.m.