Triple
T11369972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ted Ligety |
E269315
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Shred Ligety |
E269315
|
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: Shred Ligety | Statement: [Ted Ligety, nickname, Shred Ligety]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shred Ligety Context triple: [Ted Ligety, nickname, Shred Ligety]
-
A.
Ted Ligety
chosen
Ted Ligety is an American alpine ski racer renowned for his dominance in giant slalom, including multiple Olympic and World Championship gold medals.
-
B.
Jeff Shiffrin
Jeff Shiffrin was an American anesthesiologist and avid ski racing enthusiast best known as the father and early mentor of Olympic and World Cup champion alpine skier Mikaela Shiffrin.
-
C.
Bode Miller
Bode Miller is an American alpine ski racer and multiple Olympic and World Championship medalist known for his aggressive, risk-taking style on the slopes.
-
D.
Taylor Shiffrin
Taylor Shiffrin is the brother of American alpine ski champion Mikaela Shiffrin.
-
E.
Jamie Anderson
Jamie Anderson is an American professional snowboarder best known for winning the inaugural women's slopestyle gold medal at the 2014 Winter Olympics.
- 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_69d6aacca1048190b39dbbc2174616fa |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea89e1148190b0ca29db9d7e2cbd |
completed | April 9, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b7ee695c8190851ee2adb3e38738 |
completed | April 20, 2026, 5:21 a.m. |
Created at: April 8, 2026, 9:33 p.m.