Triple
T6641000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amasis II |
E150584
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Sais |
E27217
|
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: Sais | Statement: [Amasis II, capital, Sais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sais Context triple: [Amasis II, capital, Sais]
-
A.
Sais
chosen
Sais was an ancient Egyptian city in the western Nile Delta that served as a significant religious and political center, especially prominent during the 26th (Saite) Dynasty.
-
B.
Saisiyat
The Saisiyat are one of Taiwan’s indigenous Austronesian-speaking peoples, known for their distinctive culture and the legendary Pasta’ay (Dwarf) ritual.
-
C.
Saffais
Saffais is a small commune in the Meurthe-et-Moselle department of northeastern France.
-
D.
Saharias
Saharias are an indigenous tribal community of central India, traditionally known as forest dwellers and laborers with distinct cultural practices and socio-economic challenges.
-
E.
Sousel
Sousel is a municipality in Portugal’s Alentejo region, known for its rural landscape, agricultural activities, and traditional whitewashed architecture.
- 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_69c687f1a3048190828b7342f7125d5c |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6aff42c748190b818cf55f83647cb |
completed | March 27, 2026, 4:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70aea6d608190a6e58f46f69a574a |
completed | March 27, 2026, 10:55 p.m. |
Created at: March 27, 2026, 2 p.m.