Triple
T9992679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indonesian occupation of East Timor |
E196924
|
entity |
| Predicate | capitalDuringOccupation |
P17922
|
FINISHED |
| Object | Dili |
E33211
|
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: Dili | Statement: [Indonesian occupation of East Timor, capitalDuringOccupation, Dili]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dili Context triple: [Indonesian occupation of East Timor, capitalDuringOccupation, Dili]
-
A.
Dili
chosen
Dili is the coastal capital and largest city of Timor-Leste, serving as its political, economic, and cultural center.
-
B.
Ikalanga
Ikalanga is a Bantu language spoken primarily by the Kalanga people in Botswana and southwestern Zimbabwe.
-
C.
Winaray
Winaray is an Austronesian language spoken primarily in the Eastern Visayas region of the Philippines, particularly in Samar, northern Leyte, and nearby areas.
-
D.
Kwéyòl
Kwéyòl is a French-based Creole language spoken primarily in the Lesser Antilles, notably in Saint Lucia and Dominica.
-
E.
Pipile
Pipile is a genus of medium-sized, arboreal guans—turkey-like birds native to Neotropical forests in Central and South America.
- 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcb96c7308190902802ef5df764c1 |
completed | April 2, 2026, 1:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2582ac03481908e76c10218f419d5 |
completed | April 5, 2026, 12:40 p.m. |
Created at: March 30, 2026, 8:50 p.m.