Triple
T17268000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erlangga |
E419177
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Watan Mas |
E419186
|
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: Watan Mas | Statement: [Erlangga, capital, Watan Mas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Watan Mas Context triple: [Erlangga, capital, Watan Mas]
-
A.
Watan Mas
chosen
Watan Mas is a fictional capital city in the Indonesian novel "Airlangga," serving as the political and cultural center of the story's kingdom.
-
B.
Wahatoya
Wahatoya is the traditional name for Colorado’s twin Spanish Peaks, a prominent pair of volcanic mountains that serve as a well-known landmark on the eastern flank of the Sangre de Cristo Range.
-
C.
Mukaishima
Mukaishima is an island in Japan’s Seto Inland Sea that serves as one of the key waypoints along the scenic Shimanami Kaido cycling and driving route.
-
D.
Wazanaki
Wazanaki are the Zanaki people of Tanzania, a Bantu-speaking ethnic group traditionally living near Lake Victoria.
-
E.
Eniwa
Eniwa is a city in Hokkaido, Japan, known for its natural scenery, parks, and proximity to Sapporo.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42f4683c4819083a210255662136c |
completed | April 19, 2026, 1:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0179482a348190a00dd3cd5076431e |
completed | May 11, 2026, 6:38 a.m. |
Created at: April 10, 2026, 5:40 a.m.