Triple
T17894982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiat Ferroviaria |
E447408
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | ETR 460 |
—
|
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: ETR 460 | Statement: [Fiat Ferroviaria, notableProduct, ETR 460]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ETR 460 Context triple: [Fiat Ferroviaria, notableProduct, ETR 460]
-
A.
ETR 460
chosen
ETR 460 is an Italian high-speed tilting trainset used primarily for fast intercity passenger services.
-
B.
ETR 450
The ETR 450 is an Italian high-speed tilting trainset introduced in the late 1980s for Trenitalia’s Eurostar services, notable as one of the first production Pendolino trains.
-
C.
ETR 470
ETR 470 is an Italian-designed high-speed tilting electric multiple unit train used primarily for international EuroCity services in Europe.
-
D.
ETR 600
The ETR 600 is a class of Italian high-speed tilting electric multiple unit trains used for fast intercity and international services.
-
E.
ETR 480
ETR 480 is an Italian high-speed tilting electric multiple unit train used primarily for long-distance passenger services in Europe.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7eb4f48190951e26975b57873b |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:19 a.m.