Triple
T3162809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Timur |
E66140
|
entity |
| Predicate | legitimizedRuleBy |
P19049
|
FINISHED |
| Object | marriage into Genghisid line |
—
|
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: marriage into Genghisid line | Statement: [Timur, legitimizedRuleBy, marriage into Genghisid line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legitimizedRuleBy Context triple: [Timur, legitimizedRuleBy, marriage into Genghisid line]
-
A.
legitimizedBy
Indicates that something gains legal, formal, or social validity as a result of the authority, action, or endorsement of another entity.
-
B.
alsoRuled
Indicates that two or more entities shared ruling authority over the same domain or subjects, either concurrently or at different times.
-
C.
helpedLegitimize
chosen
Indicates that one entity’s actions or support contributed to making another entity appear more credible, acceptable, or officially recognized.
-
D.
hasLegalAuthorityFrom
Indicates that one entity possesses formal legal power, rights, or authorization that originates from or is granted by another entity.
-
E.
isRuleGoverned
Indicates that an entity’s behavior, structure, or operation is determined and constrained by explicit rules or formal regulations.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada61a4b8481908897a8d39d94c2f4 |
completed | March 8, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfe0a948190928f2201d671c654 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.