Triple
T2388863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Maine |
E48893
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Lyman, Maine |
E527411
|
NE FINISHED |
How this triple was built (2 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: Lyman, Maine | Statement: [Southern Maine, contains, Lyman, Maine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyman, Maine Context triple: [Southern Maine, contains, Lyman, Maine]
-
A.
Lyman, Maine
chosen
Lyman, Maine is a small rural town in York County known for its lakes, forests, and residential communities within southern Maine.
-
B.
Lovell, Maine
Lovell, Maine is a small rural town in Oxford County known for its scenic lakes and mountains in western Maine.
-
C.
Newfield, Maine
Newfield, Maine is a small rural town in southwestern Maine known for its forests, lakes, and historic village character.
-
D.
Blaine, Maine
Blaine, Maine is a small rural town located in northeastern Maine near the Canadian border, within Aroostook County’s agricultural region.
-
E.
Chamberlain, Maine
Chamberlain, Maine is a fictional small coastal town in Stephen King's works, notably serving as the primary setting of his novel "Carrie."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7dca9248190b634ae9e02f6899a |
completed | March 7, 2026, 6:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83c2fa16c8190b03ed4d47b6090e7 |
completed | March 28, 2026, 8:38 p.m. |
Created at: March 4, 2026, 7:57 p.m.