Triple
T9219049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Cherbourg railway |
E221312
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object | TER Normandie |
E206987
|
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: TER Normandie | Statement: [Paris–Cherbourg railway, hasService, TER Normandie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TER Normandie Context triple: [Paris–Cherbourg railway, hasService, TER Normandie]
-
A.
TER Normandie
chosen
TER Normandie is a regional rail service network operated by SNCF that connects cities and towns throughout the Normandy region of France.
-
B.
Normandy SR-2
The Normandy SR-2 is a highly advanced stealth frigate and primary player starship in the Mass Effect video game series, serving as Commander Shepard’s main base of operations.
-
C.
Super Étendard aircraft
The Super Étendard aircraft is a French carrier-based strike fighter best known for its Exocet missile attacks during the Falklands War.
-
D.
SNCASO SO.30 Bretagne
The SNCASO SO.30 Bretagne was a post-World War II French twin-engine airliner designed for medium-range passenger and mail transport.
-
E.
Gourette
Gourette is a French mountain ski resort village in the Pyrenees, known for its alpine slopes and scenic high-altitude setting.
- 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_69ca83eae42c8190a0ea9e040710a277 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda730f688190b64b2cc8c4898ac3 |
completed | April 1, 2026, 8:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0662c28648190979cf786fc35ab75 |
completed | April 4, 2026, 1:15 a.m. |
Created at: March 30, 2026, 7:27 p.m.