Triple
T6794338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | County of Maine |
E156014
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Perche |
E258304
|
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: Perche | Statement: [County of Maine, borders, Perche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perche Context triple: [County of Maine, borders, Perche]
-
A.
Perche
chosen
Perche is a historic rural region in northwestern France known for its rolling countryside, forests, and traditional manors.
-
B.
Pero
Pero is a West Chadic language spoken in parts of Nigeria.
-
C.
Pitiüses
The Pitiüses are a small Mediterranean archipelago comprising the Spanish Balearic Islands of Ibiza and Formentera and their surrounding islets.
-
D.
Pischa
Pischa is a mountain area and ski region near Davos in the Swiss Alps, known for its freeride terrain and winter sports opportunities.
-
E.
Perske
Perske is the birth surname of American actress and cultural icon Lauren Bacall.
- 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_69c6881844448190a65822d9b39d7f88 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d2c59648819081736d27d52d957f |
completed | March 27, 2026, 6:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a90dfb081909120e8502b26a88b |
completed | March 28, 2026, 12:02 a.m. |
Created at: March 27, 2026, 2:15 p.m.