Triple
T20790813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Seong of Baekje |
E511769
|
entity |
| Predicate | alliedWith |
P37
|
FINISHED |
| Object | Gaya |
—
|
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: Gaya | Statement: [King Seong of Baekje, alliedWith, Gaya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gaya Context triple: [King Seong of Baekje, alliedWith, Gaya]
-
A.
Gaya
Gaya is a historic city in the Indian state of Bihar, renowned as a major Hindu and Buddhist pilgrimage center, especially for the Vishnupad Temple and its proximity to Bodh Gaya.
-
B.
Gaya
Gaya is a historic town and important urban center in northern Nigeria’s Kano State.
-
C.
Gaya
chosen
Gaya was an ancient Korean confederacy of city-states known for its advanced iron culture and maritime trade, located in the southern part of the Korean Peninsula.
-
D.
Giha
Giha is an alternate name for the Ha language, a Bantu language spoken primarily in western Tanzania.
-
E.
Geisa
Geisa is a small historic town in the state of Thuringia in central Germany, near the former inner-German border.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c29010508190bf2cf577d7f64754 |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.