Triple
T9806116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uji City |
E237957
|
entity |
| Predicate | famousProduct |
P1448
|
FINISHED |
| Object | Uji matcha |
E517563
|
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: Uji matcha | Statement: [Uji City, famousProduct, Uji matcha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uji matcha Context triple: [Uji City, famousProduct, Uji matcha]
-
A.
Uji tea
chosen
Uji tea is a renowned Japanese green tea celebrated for its high quality and long history of production in the Uji region near Kyoto.
-
B.
Gamocha
Gamocha is a traditional Assamese handwoven cloth, typically white with red borders and motifs, used in cultural rituals, ceremonies, and as a symbol of respect in Assam, India.
-
C.
Maza
Maza is a Spanish-language surname notably borne by Margarita Maza de Juárez, the wife of Mexican president Benito Juárez.
-
D.
Uke Mochi
Uke Mochi is a Shinto goddess of food and fertility, known for producing sustenance from her body and for being slain by the moon god Tsukuyomi.
-
E.
Kerketeas
Kerketeas is a prominent mountain on the Greek island of Samos, known for its rugged terrain and significant elevation.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7cb9588190953a063cb7b9e29e |
completed | April 1, 2026, 11:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1c45878e481908aa2098eceb44256 |
completed | April 5, 2026, 2:09 a.m. |
Created at: March 30, 2026, 8:29 p.m.