Triple
T718803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rumford, Maine |
E14369
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object |
Peru, Maine
Peru, Maine is a small rural town in Oxford County known for its scenic western Maine landscape and close-knit community.
|
E168754
|
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: Peru, Maine | Statement: [Rumford, Maine, adjacentTo, Peru, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peru, Maine Context triple: [Rumford, Maine, adjacentTo, Peru, Maine]
-
A.
Strong, Maine
Strong, Maine is a small rural town in western Maine known historically for its lumber and toothpick manufacturing industries.
-
B.
Maine
Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
-
C.
Maine
Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
-
D.
Norway, Maine
Norway, Maine is a small New England town known for its historic downtown, lakes and outdoor recreation, located in western Maine.
-
E.
Levant, Maine
Levant, Maine is a small rural town located in Penobscot County in central Maine, known for its agricultural character and close proximity to the city of Bangor.
- 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: Peru, Maine Triple: [Rumford, Maine, adjacentTo, Peru, Maine]
Generated description
Peru, Maine is a small rural town in Oxford County known for its scenic western Maine landscape and close-knit community.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Peru, Maine Target entity description: Peru, Maine is a small rural town in Oxford County known for its scenic western Maine landscape and close-knit community.
-
A.
Strong, Maine
Strong, Maine is a small rural town in western Maine known historically for its lumber and toothpick manufacturing industries.
-
B.
Maine
Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
-
C.
Maine
Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
-
D.
Norway, Maine
Norway, Maine is a small New England town known for its historic downtown, lakes and outdoor recreation, located in western Maine.
-
E.
Levant, Maine
Levant, Maine is a small rural town located in Penobscot County in central Maine, known for its agricultural character and close proximity to the city of Bangor.
- 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_69a4934a36e081909e7abef98b898a4e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a58d4c3c8190ad4527d14bca5e6e |
completed | March 1, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad15866b448190b20334eddca756eb |
completed | March 8, 2026, 6:21 a.m. |
| NEDg | Description generation | batch_69ad164d4cfc8190a1be23c814b6b18f |
completed | March 8, 2026, 6:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad16a5c76c8190a0bb3ccf5557b1b0 |
completed | March 8, 2026, 6:26 a.m. |
Created at: March 1, 2026, 7:37 p.m.