Triple
T8251688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Nile State |
E192972
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object | Berta |
E255792
|
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: Berta | Statement: [Blue Nile State, hasEthnicGroup, Berta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berta Context triple: [Blue Nile State, hasEthnicGroup, Berta]
-
A.
Berta
Berta is the sharp-tongued, no-nonsense housekeeper known for her sarcastic humor on the sitcom "Two and a Half Men."
-
B.
Berta
Berta is a fictional character in Paulo Coelho’s novel "The Devil and Miss Prym," serving as one of the villagers whose life and choices reflect the book’s central moral and spiritual dilemmas.
-
C.
Berta
chosen
Berta is a Nilo-Saharan language spoken primarily in parts of Sudan and Ethiopia.
-
D.
Frieda
Frieda is a 1947 British drama film produced by Michael Balcon that explores post-World War II tensions and prejudice in England.
-
E.
Huberta
Huberta is a feminine given name of Dutch origin, used in full or as part of compound names such as Everdine Huberta van Wijnbergen.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb78ca4b0881909bb1fb550dba59e7 |
completed | March 31, 2026, 7:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd3540a0988190b8e48988279403db |
completed | April 1, 2026, 3:09 p.m. |
Created at: March 30, 2026, 5:48 p.m.