Triple
T12111576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Itsekiri |
E288442
|
entity |
| Predicate | settlementArea |
P82
|
FINISHED |
| Object | Koko |
E288184
|
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: Koko | Statement: [Itsekiri, settlementArea, Koko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koko Context triple: [Itsekiri, settlementArea, Koko]
-
A.
Koko
Koko was a canine actor best known for playing the title role in the Australian film "Red Dog."
-
B.
Koko
Koko is a popular Afrobeat/afropop song by Nigerian musician D'banj that helped cement his status as a leading figure in contemporary African music.
-
C.
Koko
chosen
Koko is a prominent Itsekiri town in Nigeria’s Niger Delta, known historically as a key riverine trading and port community.
-
D.
Koko Nor
Koko Nor, also known as Qinghai Lake, is the largest saltwater lake in China, located on the northeastern edge of the Tibetan Plateau.
-
E.
Kiko
Kiko is the Crown Princess of Japan and the wife of Crown Prince Akishino, a prominent member of the Japanese imperial family.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9156709288190b4684cb19037dc38 |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f67d58d08190be45fb49f0084b49 |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:49 p.m.