Triple
T20976239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elwana people |
E516632
|
entity |
| Predicate | ethnonym |
P4709
|
FINISHED |
| Object | Elwana |
—
|
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: Elwana | Statement: [Elwana people, ethnonym, Elwana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elwana Context triple: [Elwana people, ethnonym, Elwana]
-
A.
Elwana
chosen
Elwana is a lesser-known Cushitic language spoken by the Elwana people in parts of Kenya.
-
B.
Lilibet Ziller Hagel
Lilibet Ziller Hagel is the wife of former U.S. Secretary of Defense and senator Chuck Hagel and a member of his long-time family and political support network.
-
C.
Hailie Sahar
Hailie Sahar is an American transgender actress and activist best known for her groundbreaking role on the FX series "Pose."
-
D.
Jessalynn Siwa
Jessalynn Siwa is a dance instructor and reality television personality best known as the mother and manager of JoJo Siwa on shows like Dance Moms.
-
E.
Liza Koshy
Liza Koshy is an American comedian, actress, and internet personality who rose to fame on Vine and YouTube before transitioning into mainstream film and television roles.
- 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_69e0b4fee5ac8190875fa9ceba1a5e5e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fba3df2081908c1db5f8610ba43d |
completed | April 21, 2026, 4:23 a.m. |
Created at: April 16, 2026, 1:47 p.m.