Triple
T20473702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | amiibo |
E502258
|
entity |
| Predicate | announcedAt |
P430
|
FINISHED |
| Object | E3 2014 |
—
|
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: E3 2014 | Statement: [amiibo, announcedAt, E3 2014]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: E3 2014 Context triple: [amiibo, announcedAt, E3 2014]
-
A.
E3
E3 is an airport departure gate located within Concourse E.
-
B.
Global E3
Global E3 is an international consortium that facilitates engineering student exchanges and study-abroad opportunities among universities worldwide.
-
C.
Electronic Entertainment Expo
chosen
The Electronic Entertainment Expo (E3) is a major annual trade event where video game publishers, developers, and hardware manufacturers showcase upcoming games and gaming technologies to industry professionals and media.
-
D.
D.I.C.E. Summit 2017
D.I.C.E. Summit 2017 was an annual video game industry conference in Las Vegas that brought together developers, executives, and creators for talks, networking, and the presentation of the prestigious D.I.C.E. Awards.
-
E.
TGS
TGS is the fictional sketch comedy show within the television series "30 Rock," serving as the workplace backdrop for the main characters.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e699639eec81908f8bd24877b2b876 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.