Triple
T1886998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Line 1 |
E39985
|
entity |
| Predicate | rollingStock |
P1305
|
FINISHED |
| Object | MP 89 CA |
E206991
|
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: MP 89 CA | Statement: [Paris Métro Line 1, rollingStock, MP 89 CA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MP 89 CA Context triple: [Paris Métro Line 1, rollingStock, MP 89 CA]
-
A.
MP 89
chosen
MP 89 is a rubber-tyred Paris Métro train model introduced in the 1990s, known for its modern design, automated operation on some lines, and improved passenger comfort and capacity.
-
B.
CA 99
CA 99 is a major north–south state highway running through California’s Central Valley, connecting cities such as Bakersfield, Fresno, and Sacramento.
-
C.
CA 82
CA 82 is a major state highway in California that follows the historic El Camino Real corridor through the San Francisco Peninsula and Silicon Valley.
-
D.
MP 05
MP 05 is a rubber-tyred, fully automated train model used on the Paris Métro, notably on Line 1 and Line 14.
-
E.
M998
The M998 is a basic cargo and troop carrier version of the U.S. military's High Mobility Multipurpose Wheeled Vehicle (HMMWV) family.
- 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_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb121a3cc81909c60ac65627142d1 |
completed | March 7, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69addf63863881908efd8010db14b8a8 |
completed | March 8, 2026, 8:43 p.m. |
Created at: March 4, 2026, 7:34 p.m.