Triple
T17376154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King of Kediri |
E422443
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Daha |
—
|
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: Daha | Statement: [King of Kediri, hasCapital, Daha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daha Context triple: [King of Kediri, hasCapital, Daha]
-
A.
Daha
chosen
Daha was a prominent historical city in East Java that served as the political and cultural center of the medieval Kediri Kingdom in Indonesia.
-
B.
Darende
Darende is a historic district and town in eastern Turkey known for its natural scenery, religious sites, and cultural heritage within Malatya Province.
-
C.
Dua
Dua is the first name of Dua Lipa, a British-Albanian pop singer and songwriter known for hits like "New Rules" and "Levitating."
-
D.
Dalia
Dalia is a central love interest and salon owner in the comedy film "You Don’t Mess with the Zohan," portrayed as a strong, independent Palestinian woman who becomes romantically involved with the title character.
-
E.
Dalia
Dalia is a supporting character in Disney’s 2019 live-action adaptation of Aladdin, serving as Princess Jasmine’s handmaiden and close confidante.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a6ddbd081908908b953597977d2 |
completed | April 19, 2026, 2:14 a.m. |
Created at: April 10, 2026, 5:45 a.m.