Triple
T17881818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiunga |
E447103
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | Daru |
—
|
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: Daru | Statement: [Kiunga, connectedTo, Daru]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daru Context triple: [Kiunga, connectedTo, Daru]
-
A.
Daru
Daru is the central schoolteacher protagonist in the film "Loin des hommes," who faces a moral dilemma while escorting an Arab prisoner across the Algerian desert during the war of independence.
-
B.
Daru
chosen
Daru is a small coastal town and island in southwestern Papua New Guinea, known as an administrative and fishing center near the mouth of the Fly River.
-
C.
Taygi
Taygi is a lesser-known Samoyedic language of the Uralic family traditionally spoken by an indigenous group in northern Siberia.
-
D.
Tsaangi
Tsaangi is a Bantu language of Central Africa closely related to Njebi and spoken by communities in Gabon.
-
E.
Dugu
Dugu is a semi-legendary figure sometimes cited as an early founder of the Sayfawa dynasty, the long-ruling royal house of the Kanem-Bornu Empire in Central Africa.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0f40fc8190b2e615b41829f5df |
completed | April 19, 2026, 9:10 a.m. |
Created at: April 10, 2026, 10:18 a.m.