Triple
T23206551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince of Anxi |
E580472
|
entity |
| Predicate | heldBy |
P8
|
FINISHED |
| Object | Manggala |
—
|
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: Manggala | Statement: [Prince of Anxi, heldBy, Manggala]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manggala Context triple: [Prince of Anxi, heldBy, Manggala]
-
A.
Manggala
chosen
Manggala was a Mongol prince of the 13th century, notable as one of the sons of the Yuan dynasty founder Kublai Khan.
-
B.
Manggar
Manggar is a coastal town on Belitung Island in Indonesia, known for its tin mining history and numerous traditional coffee shops.
-
C.
Watubangga
Watubangga is a regional dialect of the Tolaki language spoken by communities in Southeast Sulawesi, Indonesia.
-
D.
Pakualaman
Pakualaman is a small hereditary Javanese princely state and court within Yogyakarta, established in the 19th century as a minor parallel to the main sultanate.
-
E.
Tumpang
Tumpang is a subdistrict in Malang Regency, East Java, Indonesia, known for its proximity to historical temples and as a gateway to the Bromo-Tengger-Semeru area.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1907cd62c8190afee1e963b170727 |
completed | April 29, 2026, 5 a.m. |
Created at: April 17, 2026, 4:07 p.m.