Triple
T17072406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Sanjō |
E414254
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Imperial Princess Teishi |
E1236831
|
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: Imperial Princess Teishi | Statement: [Emperor Sanjō, child, Imperial Princess Teishi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Imperial Princess Teishi Context triple: [Emperor Sanjō, child, Imperial Princess Teishi]
-
A.
Princess Teishi
chosen
Princess Teishi was a Heian-period Japanese imperial princess and consort, known for her connections to the powerful Fujiwara clan.
-
B.
Princess Toshi
Princess Toshi, formally Princess Aiko, is the only child of Emperor Naruhito and Empress Masako of Japan and a member of the Japanese imperial family.
-
C.
Princess Seishi
Princess Seishi was a Japanese imperial princess of the early Heian period who became the consort of Emperor Junna.
-
D.
Empress Tudan
Empress Tudan was a consort of Emperor Zhangzong of the Jurchen-led Jin dynasty in China, holding the title of empress during his reign.
-
E.
Princess of Asaka
Princess of Asaka is a Japanese imperial title traditionally borne by female members of the Asaka branch of the Imperial House of Japan.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc1b7d48190979a848b4188cb22 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012edbce988190a784448ba8a258a5 |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:34 a.m.