Triple
T20719146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ancre River |
E509261
|
entity |
| Predicate | nameInFrench |
P6538
|
FINISHED |
| Object | Ancre |
—
|
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: Ancre | Statement: [Ancre River, nameInFrench, Ancre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ancre Context triple: [Ancre River, nameInFrench, Ancre]
-
A.
Tournelle
Tournelle refers to the historical riverside district and former tower area in Paris that gave its name to the Pont de la Tournelle.
-
B.
Pontgouin
Pontgouin is a small commune in northern France’s Eure-et-Loir department, known for its rural setting and the Eure River running through it.
-
C.
La Cambe
La Cambe is a commune in the Calvados department of Normandy in northwestern France, known for its proximity to major World War II sites including a large German war cemetery.
-
D.
Ancre valley
chosen
Ancre valley is a region in the Somme department of northern France that was a significant World War I battlefield, particularly during the Battle of the Somme.
-
E.
Boucau
Boucau is a small commune in southwestern France’s Pyrénées-Atlantiques department, near the Atlantic coast and the city of Bayonne.
- 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d39bec8190b3642b0d6d833375 |
completed | April 21, 2026, 12:16 a.m. |
Created at: April 16, 2026, 12:26 p.m.