Triple
T14898026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jukun |
E359929
|
entity |
| Predicate | historicalCapital |
P2536
|
FINISHED |
| Object | Wukari |
E341597
|
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: Wukari | Statement: [Jukun, historicalCapital, Wukari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wukari Context triple: [Jukun, historicalCapital, Wukari]
-
A.
Wukari
chosen
Wukari is a historic town in present-day Taraba State, Nigeria, long associated with the Jukun people and the traditional Wukari Federation.
-
B.
Kocaali
Kocaali is a coastal town and district in northwestern Turkey, situated along the Black Sea in Sakarya Province.
-
C.
Gumrak
Gumrak is a locality near Volgograd in Russia, historically known as the site of a World War II airfield used during the Battle of Stalingrad.
-
D.
Yakakent
Yakakent is a coastal district and town on the Black Sea in northern Turkey’s Samsun Province, known for its fishing and seaside tourism.
-
E.
Tarkarli
Tarkarli is a coastal village in Maharashtra, India, known for its pristine beaches, clear waters, and popular scuba diving and snorkeling spots.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded6084574819098033a9723f3e1c4 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b6966e88190a0ed475b22a77cf1 |
completed | May 8, 2026, 11:02 p.m. |
Created at: April 10, 2026, 2:11 a.m.