Triple
T850627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portsmouth |
E18376
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Caen |
E99797
|
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: Caen | Statement: [Portsmouth, twinTown, Caen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caen Context triple: [Portsmouth, twinTown, Caen]
-
A.
Caen
chosen
Caen is a historic city in Normandy, France, known for its medieval architecture, ties to William the Conqueror, and its role in the World War II Normandy campaign.
-
B.
Cherbourg
Cherbourg is a major French port city on the Cotentin Peninsula, known for its strategic naval harbor and cross-Channel ferry connections.
-
C.
Arromanches-les-Bains
Arromanches-les-Bains is a coastal town in Normandy, France, best known for its role in the D-Day landings and the remains of the Mulberry artificial harbor just offshore.
-
D.
Rouen
Rouen is a historic city in northern France renowned for its medieval architecture, Gothic cathedral, and association with figures like Joan of Arc and the Impressionist painter Claude Monet.
-
E.
Calais
Calais is a major French port city on the northern coast, serving as one of the primary crossing points between France and England.
- 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_69a4938b04208190b82e1df6b572c548 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac215194819099e6bc1b5df58fb3 |
completed | March 1, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a93398a6948190981e932178aee6b9 |
completed | March 5, 2026, 7:41 a.m. |
Created at: March 1, 2026, 7:38 p.m.