Triple
T2427882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 東北大学 |
E53572
|
entity |
| Predicate | 所属ネットワーク |
P2637
|
FINISHED |
| Object | 国立大学法人 |
—
|
LITERAL 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: 国立大学法人 | Statement: [東北大学, 所属ネットワーク, 国立大学法人]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属ネットワーク Context triple: [東北大学, 所属ネットワーク, 国立大学法人]
-
A.
branchNetwork
Indicates that one entity operates as a branch or local outlet within the wider organizational or operational network of another entity.
-
B.
originalNetworkName
Indicates the name of the network from which something (e.g., data, content, or a connection) originally came.
-
C.
networkServed
Indicates that a network provides connectivity or services to a particular entity or set of entities.
-
D.
network
chosen
Indicates that one entity is connected to or interacts with another through a system of relationships, communication, or information exchange.
-
E.
originalNetwork
Indicates that one entity is the original or source network from which another network or derived entity is based or obtained.
- F. None of above.
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_69ab495c44d48190b7235b23719bc3f6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abcc74a5108190a3a9631b0cc1a127 |
completed | March 7, 2026, 6:57 a.m. |
| PD | Predicate disambiguation | batch_69abc5aa1b60819081b87f7985c6cff3 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 6, 2026, 9:42 p.m.