Triple
T19070394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The World Games |
E466774
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | TWG |
—
|
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: TWG | Statement: [The World Games, shortName, TWG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TWG Context triple: [The World Games, shortName, TWG]
-
A.
TWG
chosen
TWG is the commonly used abbreviation for The World Games, an international multi-sport event featuring disciplines not contested in the Olympic Games.
-
B.
TGW
TGW is the ICAO airline designator for Scoot, a Singapore-based low-cost carrier.
-
C.
TGWU
TGWU is the commonly used abbreviation for the Transport and General Workers' Union, once one of the largest and most influential trade unions in the United Kingdom.
-
D.
GTW
GTW was the stock ticker symbol for Gateway, Inc., a former major American personal computer manufacturer known for its cow-spotted boxes and direct-to-consumer sales model.
-
E.
GTW
GTW is a family of modular articulated railcars produced by Stadler Rail, widely used for regional and commuter train services in various European countries.
- 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e19ea01c8190b9bb789da32f9a90 |
completed | April 20, 2026, 8:19 a.m. |
Created at: April 10, 2026, 12:04 p.m.