Triple
T18939400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | river Ante |
E463339
|
entity |
| Predicate | flowsNear |
P350
|
FINISHED |
| Object | Falaise |
—
|
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: Falaise | Statement: [river Ante, flowsNear, Falaise]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Falaise Context triple: [river Ante, flowsNear, Falaise]
-
A.
Falaise
chosen
Falaise is a town in Normandy, France, known for its strategic role in the Second World War, particularly during the closing of the Falaise Pocket in 1944.
-
B.
Avranches
Avranches is a historic town in northwestern France, near Mont-Saint-Michel, known for its medieval heritage and role in the liberation of Normandy during World War II.
-
C.
Pontois
Pontois is the French demonym referring to inhabitants of the commune of Pont-de-l’Isère in southeastern France.
-
D.
Harfleur
Harfleur is a historic port town in Normandy, northern France, known for its strategic importance during the Hundred Years’ War.
-
E.
Fécamp
Fécamp is a coastal town and former important fishing port in northern France, known for its historic Benedictine Palace and dramatic cliffs along the English Channel.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d3eae9b88190b6031c359090782a |
completed | April 20, 2026, 7:21 a.m. |
Created at: April 10, 2026, 11:59 a.m.