Triple
T20157699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valide Sultan |
E491616
|
entity |
| Predicate | relativeRankToSultan |
P50407
|
FINISHED |
| Object | second only to the sultan |
—
|
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: second only to the sultan | Statement: [Valide Sultan, relativeRankToSultan, second only to the sultan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeRankToSultan Context triple: [Valide Sultan, relativeRankToSultan, second only to the sultan]
-
A.
militaryRankBeforeSultan
Indicates that one entity held a specific military rank prior to becoming a sultan.
-
B.
positionRelativeToCaliph
Indicates the spatial or hierarchical position an entity holds in relation to the caliph.
-
C.
recognizedAsSultan
Indicates that an entity is acknowledged or accepted by others as holding the status or title of sultan.
-
D.
takhtRank
Indicates the hierarchical rank or position an individual holds within a takht (a formal seat or council of authority).
-
E.
rankInPrincelyOrder
chosen
Indicates the position or level an entity holds within a specified princely order or hierarchy.
- 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667e18a0c8190a2cc2b305da28047 |
completed | April 20, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69e54cfd924881909b55f3e4d3e7e070 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:34 p.m.