Triple
T20920333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bungo Province |
E515189
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object |
Funai
Funai was the historical castle town that served as the political and administrative center of Japan’s former Bungo Province on Kyushu.
|
E1457906
|
NE FINISHED |
How this triple was built (4 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: Funai | Statement: [Bungo Province, capital, Funai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Funai Context triple: [Bungo Province, capital, Funai]
-
A.
Funaki
Funaki is a Japanese surname most notably associated with Olympic gold medal-winning ski jumper Kazuyoshi Funaki.
-
B.
Nimco
Nimco is the wife of Somali-born British journalist and television news presenter Rageh Omaar.
-
C.
Kachidoki
Kachidoki is a waterfront district in Tokyo’s Chūō ward known for its high-rise residential towers, proximity to the Sumida River, and convenient access to central Tokyo.
-
D.
Sanyo-Onoda
Sanyo-Onoda is a coastal industrial city in western Japan known for its cement and chemical industries and its location along the Seto Inland Sea.
-
E.
Daiso
Daiso is a popular Japanese discount retail chain known for selling a wide variety of household goods and everyday items, often at a uniform low price.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Funai Triple: [Bungo Province, capital, Funai]
Generated description
Funai was the historical castle town that served as the political and administrative center of Japan’s former Bungo Province on Kyushu.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Funai Target entity description: Funai was the historical castle town that served as the political and administrative center of Japan’s former Bungo Province on Kyushu.
-
A.
Funaki
Funaki is a Japanese surname most notably associated with Olympic gold medal-winning ski jumper Kazuyoshi Funaki.
-
B.
Nimco
Nimco is the wife of Somali-born British journalist and television news presenter Rageh Omaar.
-
C.
Kachidoki
Kachidoki is a waterfront district in Tokyo’s Chūō ward known for its high-rise residential towers, proximity to the Sumida River, and convenient access to central Tokyo.
-
D.
Sanyo-Onoda
Sanyo-Onoda is a coastal industrial city in western Japan known for its cement and chemical industries and its location along the Seto Inland Sea.
-
E.
Daiso
Daiso is a popular Japanese discount retail chain known for selling a wide variety of household goods and everyday items, often at a uniform low price.
- F. None of above. chosen
Provenance (5 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec677338819081410cbaa2846260 |
completed | April 21, 2026, 3:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a091fc8ddc88190b863f952ecfba75b |
completed | May 17, 2026, 1:54 a.m. |
| NEDg | Description generation | batch_6a0920fa7e488190b92045b9bd619bba |
completed | May 17, 2026, 1:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09216f7b188190b327efe8e4cceae1 |
completed | May 17, 2026, 2:01 a.m. |
Created at: April 16, 2026, 12:48 p.m.