Triple
T3379331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Fontana |
E71142
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | RAI |
E140861
|
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: RAI | Statement: [Tom Fontana, employer, RAI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RAI Context triple: [Tom Fontana, employer, RAI]
-
A.
RAI
chosen
RAI is Italy’s national public broadcasting company, operating multiple television and radio channels and producing a wide range of news, entertainment, and cultural programming.
-
B.
RAI
RAI is the stock ticker symbol for Reynolds American Inc., a major U.S. tobacco company known for brands like Camel and Newport.
-
C.
Rai
Rai are an indigenous ethnic group from the eastern Himalayan region of Nepal, known for their distinct Kirati culture, languages, and traditions.
-
D.
Bell’Italia
Bell’Italia is a themed miniature recreation of iconic Italian landscapes and cities located within the Ferrari World Abu Dhabi theme park.
-
E.
Ora TV
Ora TV is a digital television network and production company co-founded by Larry King that creates and distributes original online video programming.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2ec38d88190be8c824daeca5ab6 |
completed | March 8, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3344c0698819082d856d8be7f2c18 |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:14 p.m.