Triple
T11964194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krugersdorp Game Reserve |
E284749
|
entity |
| Predicate | hasWildlife |
P965
|
FINISHED |
| Object | kudu |
E31842
|
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: kudu | Statement: [Krugersdorp Game Reserve, hasWildlife, kudu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: kudu Context triple: [Krugersdorp Game Reserve, hasWildlife, kudu]
-
A.
greater kudu
chosen
The greater kudu is a large African antelope species known for its impressive spiral horns and striking white body stripes, commonly found in woodland and savanna habitats.
-
B.
KUD
KUD is the station code used to identify Kungsträdgården metro station in the Stockholm metro system.
-
C.
KU2
KU2 is the stock ticker symbol for KUKA, a German industrial robotics and automation company.
-
D.
KUN
KUN is the IATA airport code for Kaunas Airport, a commercial international airport serving the city of Kaunas in Lithuania.
-
E.
KLu
KLu is the commonly used abbreviation for the Royal Netherlands Air Force, the aerial warfare branch of the Dutch armed forces.
- 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_69d6ab2eaeb881909f7914758f859413 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903799f948190a5dc4d3822f3ff27 |
completed | April 10, 2026, 2:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f4594054f08190b28b35f62dfb9198 |
completed | May 1, 2026, 7:41 a.m. |
Created at: April 8, 2026, 9:45 p.m.