Triple
T16596965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tirreno–Adriatico |
E403231
|
entity |
| Predicate | notableWinner |
P2766
|
FINISHED |
| Object |
Tony Rominger
Tony Rominger is a retired Swiss professional cyclist renowned for his Grand Tour victories and time-trialing prowess during the early 1990s.
|
E1222883
|
NE FINISHED |
How this triple was built (4 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: Tony Rominger | Statement: [Tirreno–Adriatico, notableWinner, Tony Rominger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Rominger Context triple: [Tirreno–Adriatico, notableWinner, Tony Rominger]
-
A.
George Hincapie
George Hincapie is an American former professional road cyclist best known as a long-time domestique for Lance Armstrong and a key figure in the U.S. Postal Service team's doping scandal.
-
B.
Andy Hampsten
Andy Hampsten is an American former professional road cyclist best known for winning the 1988 Giro d'Italia and excelling as a climber in Grand Tours.
-
C.
Chris King
Chris King is an individual known for being the subject of writing by Amy.
-
D.
Chris King
Chris King is a film editor known for his work on acclaimed documentaries, including the 2015 film "Amy" about singer Amy Winehouse.
-
E.
LeMond
LeMond is the surname of Greg LeMond, the pioneering American professional cyclist and three-time Tour de France winner.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tony Rominger Triple: [Tirreno–Adriatico, notableWinner, Tony Rominger]
Generated description
Tony Rominger is a retired Swiss professional cyclist renowned for his Grand Tour victories and time-trialing prowess during the early 1990s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tony Rominger Target entity description: Tony Rominger is a retired Swiss professional cyclist renowned for his Grand Tour victories and time-trialing prowess during the early 1990s.
-
A.
George Hincapie
George Hincapie is an American former professional road cyclist best known as a long-time domestique for Lance Armstrong and a key figure in the U.S. Postal Service team's doping scandal.
-
B.
Andy Hampsten
Andy Hampsten is an American former professional road cyclist best known for winning the 1988 Giro d'Italia and excelling as a climber in Grand Tours.
-
C.
Chris King
Chris King is an individual known for being the subject of writing by Amy.
-
D.
Chris King
Chris King is a film editor known for his work on acclaimed documentaries, including the 2015 film "Amy" about singer Amy Winehouse.
-
E.
LeMond
LeMond is the surname of Greg LeMond, the pioneering American professional cyclist and three-time Tour de France winner.
- F. None of above. chosen
Provenance (5 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_69d883880d0c81908b5fcd454e767b60 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35d723c508190b5afbda5eec5abea |
completed | April 18, 2026, 10:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00759fe6ec81908c5321dcba558269 |
completed | May 10, 2026, 12:10 p.m. |
| NEDg | Description generation | batch_6a007825547c81909230ac39761fba96 |
completed | May 10, 2026, 12:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00788e103481908d40bbe4a3cb1695 |
completed | May 10, 2026, 12:22 p.m. |
Created at: April 10, 2026, 5:16 a.m.