Triple
T16366608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | International Golf Federation |
E397451
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | IGF |
E831106
|
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: IGF | Statement: [International Golf Federation, shortName, IGF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IGF Context triple: [International Golf Federation, shortName, IGF]
-
A.
IGF
IGF is a Japanese professional wrestling and mixed martial arts promotion founded by Antonio Inoki.
-
B.
IGF
chosen
IGF is a global multistakeholder platform convened by the United Nations to discuss public policy issues related to the governance and development of the internet.
-
C.
IGSF
IGSF is an academic unit at McGill University dedicated to interdisciplinary teaching and research on gender, sexuality, and feminist studies.
-
D.
IG
IG is the commonly used abbreviation for the Irish Guards, an infantry regiment of the British Army known for its ceremonial duties and operational deployments.
-
E.
IG
IG is a UK postcode area covering parts of east London and southwest Essex, including towns such as Ilford and Barking.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff3de3d88190a42cd708746c8bd0 |
completed | April 18, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dc0b3d4819089e6fba536ec8a11 |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:08 a.m.