Triple
T10204274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banzi |
E238962
|
entity |
| Predicate | hasHistoricalSite |
P1098
|
FINISHED |
| Object | Bantia |
E47124
|
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: Bantia | Statement: [Banzi, hasHistoricalSite, Bantia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bantia Context triple: [Banzi, hasHistoricalSite, Bantia]
-
A.
Bantia
chosen
Bantia was an ancient Oscan-speaking city in southern Italy, notable for yielding important inscriptions that illuminate the Oscan language and Italic legal traditions.
-
B.
Pangcah
Pangcah is the self-designation of the Amis, one of the largest Indigenous Austronesian peoples of Taiwan, known for their distinct language and rich cultural traditions.
-
C.
Bachok
Bachok is a coastal town and district in the Malaysian state of Kelantan, known for its beaches and traditional Malay fishing villages.
-
D.
Pakpak Keppas
Pakpak Keppas is a regional dialect of the Pakpak Dairi language spoken by the Pakpak ethnic community in parts of North Sumatra, Indonesia.
-
E.
Toboali
Toboali is a coastal town and administrative center in the southern part of Bangka Island in Indonesia, known historically for its tin mining activities.
- 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_69ca84e1ea088190b38162e43d4cfa8f |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdeed6fd0081908f8afad1ef4c6bff |
completed | April 2, 2026, 4:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d318026ee88190961288fdbde73b08 |
completed | April 6, 2026, 2:18 a.m. |
Created at: March 30, 2026, 9:14 p.m.