Triple
T14884516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunwolves |
E350086
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | Sunwolves |
E350086
|
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: Sunwolves | Statement: [Sunwolves, shortName, Sunwolves]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sunwolves Context triple: [Sunwolves, shortName, Sunwolves]
-
A.
Sunwolves
chosen
The Sunwolves were a professional Japanese rugby union team that competed in the international Super Rugby competition.
-
B.
Seoul Dynasty
Seoul Dynasty is a professional esports team based in Seoul, South Korea that competes in Blizzard Entertainment’s Overwatch League.
-
C.
ZSC Lions
ZSC Lions is a professional ice hockey club from Zürich, Switzerland, known as one of the country’s most successful and prominent teams.
-
D.
T-Wolves Gaming
T-Wolves Gaming is the official NBA 2K League esports team affiliated with the NBA's Minnesota Timberwolves.
-
E.
LG Cheetahs
LG Cheetahs was a professional South Korean football club that competed in the K League and later became known as FC Seoul.
- 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_69d822ee4f408190b6ac3b2fa434f0df |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded5f4598081908735e8d7dfce8074 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b5d0a208190b2490c86b15a42db |
completed | May 8, 2026, 11:01 p.m. |
Created at: April 10, 2026, 1:56 a.m.