Triple
T15257425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sher Afgan Khan |
E364682
|
entity |
| Predicate | marriageToNurJahan |
P45667
|
FINISHED |
| Object | took place before Jahangir’s accession |
—
|
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: took place before Jahangir’s accession | Statement: [Sher Afgan Khan, marriageToNurJahan, took place before Jahangir’s accession]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageToNurJahan Context triple: [Sher Afgan Khan, marriageToNurJahan, took place before Jahangir’s accession]
-
A.
relationToNurJahan
chosen
Indicates a relationship or connection that an entity has specifically to Nur Jahan.
-
B.
marriedToEmperor
Indicates that one entity is the spouse of an emperor, signifying a marital relationship to a reigning or titled emperor.
-
C.
predecessorAsMughalEmperor
Indicates that one entity served as the Mughal emperor immediately before another entity in the line of succession.
-
D.
successorAsNawabOfAwadh
Indicates that one entity became the next Nawab of Awadh, directly succeeding another in that position.
-
E.
marriedToFutureMonarch
Indicates that one person is married to another person who will become a monarch in the future.
- 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_69d85a0f08408190b3c3259ae35d79d2 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0084b97908190b3bf7ea7bd75bdc0 |
completed | April 15, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69deca8d1bd48190a4b94f29b425e335 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:13 a.m.