Triple
T22916699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IMG |
E568749
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object | IMG Events |
—
|
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: IMG Events | Statement: [IMG, hasDivision, IMG Events]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IMG Events Context triple: [IMG, hasDivision, IMG Events]
-
A.
IMG Events
chosen
IMG Events is a global sports, fashion, and entertainment events management and production company within the WME-IMG (Endeavor) group.
-
B.
EventsML
EventsML is an XML-based standard for describing, exchanging, and managing news and media event information across global news organizations.
-
C.
Events ACT
Events ACT is a government-backed events agency in Canberra responsible for planning and delivering major public festivals and attractions in Australia’s capital.
-
D.
Media Independent Event Service
Media Independent Event Service is a component of the IEEE 802.21 framework that provides a standardized way to report and manage network-related events across heterogeneous access technologies to support seamless handovers.
-
E.
Main Events
Main Events is a prominent American boxing promotion company known for organizing major championship bouts and developing top-tier fighters.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1807a14648190b5d5f7d926f19320 |
completed | April 29, 2026, 3:52 a.m. |
Created at: April 17, 2026, 3:42 p.m.