Triple
T38378846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manghit |
E893701
|
entity |
| Predicate | notableRulerClanFor |
P111063
|
FINISHED |
| Object | Emirate of Bukhara |
E45081
|
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: Emirate of Bukhara | Statement: [Manghit, notableRulerClanFor, Emirate of Bukhara]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableRulerClanFor Context triple: [Manghit, notableRulerClanFor, Emirate of Bukhara]
-
A.
recognizedAsRulersBy
Indicates that certain entities are acknowledged or accepted by others as their legitimate rulers or authorities.
-
B.
notableClans
chosen
Indicates that there exists a significant or historically important clan associated with the subject.
-
C.
notableDaimyo
Indicates that a person held the status of a daimyō and is recognized as particularly prominent or historically significant among daimyō.
-
D.
associatedDynastyRuler
Indicates a relationship where a dynasty is linked to the ruler who governed or is historically connected with it.
-
E.
foundingEmperorFromClan
Indicates that the founding emperor belongs to or originates from a specified clan.
- F. None of above.
Provenance (4 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_69f76e4b1f748190a380696a16eae4a2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a42157eaa2081908fe15dd71f7b9589 |
completed | June 29, 2026, 6:49 a.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:31 p.m.