Triple
T15087844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hancock County |
E360327
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Castine
Castine is a historic coastal town in Maine known for its well-preserved architecture, maritime heritage, and role in early American history.
|
E1193353
|
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: Castine | Statement: [Hancock County, contains, Castine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Castine Context triple: [Hancock County, contains, Castine]
-
A.
Masset
Masset is a small coastal village on the northern tip of Haida Gwaii in British Columbia, Canada, known as a key Haida community and gateway to the archipelago.
-
B.
Calais, Maine
Calais, Maine is a small city on the St. Croix River along the U.S.–Canada border in eastern Maine, known historically for lumber, shipbuilding, and cross-border trade.
-
C.
Palermo, Maine
Palermo, Maine is a small rural town in central Maine known for its lakes, forests, and quiet residential character.
-
D.
Carthage, Maine
Carthage, Maine is a small rural town in western Maine known for its mountainous landscape and outdoor recreational opportunities.
-
E.
Kittery, Maine
Kittery, Maine is a historic coastal town at the southern tip of the state, known for its naval shipyard and outlet shopping district.
- 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: Castine Triple: [Hancock County, contains, Castine]
Generated description
Castine is a historic coastal town in Maine known for its well-preserved architecture, maritime heritage, and role in early American history.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Castine Target entity description: Castine is a historic coastal town in Maine known for its well-preserved architecture, maritime heritage, and role in early American history.
-
A.
Masset
Masset is a small coastal village on the northern tip of Haida Gwaii in British Columbia, Canada, known as a key Haida community and gateway to the archipelago.
-
B.
Calais, Maine
Calais, Maine is a small city on the St. Croix River along the U.S.–Canada border in eastern Maine, known historically for lumber, shipbuilding, and cross-border trade.
-
C.
Palermo, Maine
Palermo, Maine is a small rural town in central Maine known for its lakes, forests, and quiet residential character.
-
D.
Carthage, Maine
Carthage, Maine is a small rural town in western Maine known for its mountainous landscape and outdoor recreational opportunities.
-
E.
Kittery, Maine
Kittery, Maine is a historic coastal town at the southern tip of the state, known for its naval shipyard and outlet shopping district.
- 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_69d85a035aa88190b52a139d3a1b7b6d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00276d1608190bc310d5b86ecd1d5 |
completed | April 15, 2026, 9:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe46436048190b79d1d18a179617b |
completed | May 10, 2026, 1:50 a.m. |
| NEDg | Description generation | batch_69ffe5ced2dc8190922b910d1a6c08d3 |
completed | May 10, 2026, 1:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffe687c204819092a4a8de0b9d624d |
completed | May 10, 2026, 1:59 a.m. |
Created at: April 10, 2026, 3:03 a.m.