Triple
T4815858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tōdai-ji |
E107585
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Sangatsu-dō |
E505736
|
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: Sangatsu-dō | Statement: [Tōdai-ji, hasPart, Sangatsu-dō]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sangatsu-dō Context triple: [Tōdai-ji, hasPart, Sangatsu-dō]
-
A.
Nigatsu-dō
chosen
Nigatsu-dō is a prominent sub-temple hall within the Tōdai-ji complex in Nara, Japan, renowned for its annual Shuni-e (Omizutori) Buddhist repentance ceremony.
-
B.
Kizoku-in
Kizoku-in was the upper house of Japan’s prewar Imperial Diet, composed mainly of nobility and imperial appointees.
-
C.
Hōzōmon
Hōzōmon is the grand inner gate of Sensō-ji Temple in Tokyo’s Asakusa district, known for its massive lanterns and guardian statues.
-
D.
Shoin Jinja
Shoin Jinja is a Shinto shrine in Tokyo dedicated to the influential late-Edo period thinker and educator Yoshida Shōin.
-
E.
Domyoji Tenmangu
Domyoji Tenmangu is a historic Shinto shrine in Fujiidera, Osaka Prefecture, renowned for its plum blossoms and dedication to the scholar-statesman Sugawara no Michizane.
- 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_69bd43f9efa081908314cb3e94fa1695 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6c8230888190a676695e51cb3ea4 |
completed | March 20, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69befe46b4d081908597c79135415909 |
completed | March 21, 2026, 8:23 p.m. |
Created at: March 20, 2026, 1:23 p.m.