Triple
T4109034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TGV Réseau |
E88522
|
entity |
| Predicate | trainProtectionSystem |
P40340
|
FINISHED |
| Object | TVM-300 |
E408790
|
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: TVM-300 | Statement: [TGV Réseau, trainProtectionSystem, TVM-300]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TVM-300 Context triple: [TGV Réseau, trainProtectionSystem, TVM-300]
-
A.
TVM-300
chosen
TVM-300 is a high-speed railway cab signalling and train control system used on French high-speed lines such as the LGV Nord.
-
B.
TVM-430
TVM-430 is a modern in-cab railway signaling and train protection system used on high-speed lines such as the French TGV network.
-
C.
TX-30
TX-30 is the commonly used abbreviation for Texas's 30th congressional district, a U.S. House of Representatives district centered in the Dallas area.
-
D.
TX-38
TX-38 is a U.S. congressional district in Texas represented in the House of Representatives.
-
E.
TX-35
TX-35 is the commonly used abbreviation for Texas's 35th congressional district, a U.S. House of Representatives district centered around parts of Austin and San Antonio.
- 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_69aed9484fb881909146f4c772ad277c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0b2c76fc8190b3cd9facfcd6e427 |
completed | March 9, 2026, 6:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b576a695b08190890aa4f64289d227 |
completed | March 14, 2026, 2:54 p.m. |
Created at: March 9, 2026, 3:40 p.m.