Triple
T18564393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warang Citi block |
E453724
|
entity |
| Predicate | hasScriptProperty |
P23698
|
FINISHED |
| Object | Warang_Citi |
—
|
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: Warang_Citi | Statement: [Warang Citi block, hasScriptProperty, Warang_Citi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Warang_Citi Context triple: [Warang Citi block, hasScriptProperty, Warang_Citi]
-
A.
Warang Citi
chosen
Warang Citi is an alphabetic writing system created in the 20th century for the Ho language spoken by the Ho people of eastern India.
-
B.
Kota Seribu Sungai
Kota Seribu Sungai is a nickname for Banjarmasin, a South Kalimantan city famed for its extensive river networks and floating markets.
-
C.
Kota Ukir
Kota Ukir is a nickname for Jepara, an Indonesian town renowned for its intricate woodcarving and furniture craftsmanship.
-
D.
Timika
Timika is a mining and administrative town in Papua, Indonesia, known primarily as the gateway to the Grasberg mine and the surrounding highland region.
-
E.
Kokota
Kokota is an Oceanic language spoken in the Solomon Islands, particularly on Santa Isabel Island.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53afd8114819093b57d86f8213311 |
completed | April 19, 2026, 8:28 p.m. |
Created at: April 10, 2026, 11:42 a.m.