Triple
T29533388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikeda clan |
E749267
|
entity |
| Predicate | notableBranchDomain |
P207153
|
FINISHED |
| Object | Okayama Domain |
E1113599
|
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: Okayama Domain | Statement: [Ikeda clan, notableBranchDomain, Okayama Domain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBranchDomain Context triple: [Ikeda clan, notableBranchDomain, Okayama Domain]
-
A.
notableBranch
Indicates that one entity is a particularly significant or prominent subdivision, offshoot, or branch of another entity.
-
B.
notableDomain
Indicates that there is a notable or especially significant association between an entity and a particular domain, field, or area of activity.
-
C.
principalBranchDomain
Indicates the domain over which the principal branch of a multi-valued function (such as a complex logarithm or power) is defined and considered valid.
-
D.
notableFork
Indicates that one entity is a significant fork or derivative version of another, typically diverging in a notable or influential way from the original.
-
E.
influencedBranch
Indicates that one branch, idea, or development has been shaped or affected by another preceding or related branch.
- 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_69f0bd47abb081909bd6e6a33d770fd8 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a260c366fa8819085ec36e542b9469f |
completed | June 8, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 28, 2026, 4:55 p.m.