Triple
T38390924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Count of Perche |
E899713
|
entity |
| Predicate | regionHistoricallyBordered |
P47008
|
FINISHED |
| Object | Normandy |
—
|
NE NERFINISHED |
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: Normandy | Statement: [Count of Perche, regionHistoricallyBordered, Normandy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionHistoricallyBordered Context triple: [Count of Perche, regionHistoricallyBordered, Normandy]
-
A.
historicBoundaryFor
chosen
Indicates that one entity serves as a historical boundary or border associated with another entity, typically reflecting past territorial or administrative limits.
-
B.
borderRegion
Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
-
C.
borderedBy
Indicates that one entity shares a common boundary or edge with another entity.
-
D.
borderHistory
Indicates the historical changes, events, or status of borders between entities over time.
-
E.
historicalRegionNowDividedBetween
Indicates that a historical region has been partitioned and its territory is now split between two or more present-day political or administrative entities.
- F. None of above.
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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a008e29f76881908e656dbbd7fceea3 |
completed | May 10, 2026, 1:54 p.m. |
| PD | Predicate disambiguation | batch_6a008dc01b308190bc26e69814692f82 |
completed | May 10, 2026, 1:53 p.m. |
Created at: May 3, 2026, 4:31 p.m.