Triple
T19993512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ski |
E494121
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | DJ Ski |
—
|
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: DJ Ski | Statement: [Ski, alsoKnownAs, DJ Ski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DJ Ski Context triple: [Ski, alsoKnownAs, DJ Ski]
-
A.
Frank Ski
chosen
Frank Ski is an American DJ, radio personality, and music producer known for his influential role in Atlanta’s hip-hop and club music scene.
-
B.
Jack Skiba
Jack Skiba was the husband of American singer Patti Page, one of the best-selling female vocalists of the 20th century.
-
C.
Piper Skih
Piper Skih is a musician best known for having been a member of the American alternative rock band Blue October.
-
D.
Ziller
The Ziller is a river in the Austrian state of Tyrol that flows through the Zillertal valley before joining the Inn River.
-
E.
DJ Ötzi
DJ Ötzi is an Austrian pop and schlager singer and DJ best known for his party hits like "Hey Baby" and "Anton aus Tirol," which have made him a staple of German-language apres-ski and party music.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe2036c8190b9f313215ad44e87 |
completed | April 20, 2026, 5:18 p.m. |
Created at: April 11, 2026, 3:31 p.m.