Triple
T35479382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tozama domain |
E1025426
|
entity |
| Predicate | hasObligationsTo |
P81322
|
FINISHED |
| Object | Tokugawa shogunate |
—
|
NE NERFINISHED |
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: Tokugawa shogunate | Statement: [tozama domain, hasObligationsTo, Tokugawa shogunate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasObligationsTo Context triple: [tozama domain, hasObligationsTo, Tokugawa shogunate]
-
A.
hasOngoingObligations
Indicates that an entity is currently bound by duties or responsibilities that are still in effect and not yet fulfilled or terminated.
-
B.
hasSocialObligationsTo
chosen
Indicates that one entity bears social duties, expectations, or responsibilities toward another entity.
-
C.
hasObligationForDesignees
Indicates that an entity holds a duty or responsibility on behalf of, or in relation to, specified designees.
-
D.
hasFewerObligationsThan
Indicates that one entity is subject to a smaller number or lesser extent of duties, responsibilities, or required actions compared to another entity.
-
E.
hasObligationLevel
Indicates that one entity bears a specified degree or intensity of duty, responsibility, or required action toward another entity or situation.
- 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_69f76dfadba0819083456aadcd6864ea |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.