Triple
T22249710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Khalifa family |
E549939
|
entity |
| Predicate | predecessorRulersOfBahrain |
P147547
|
FINISHED |
| Object | Persian Empire representatives |
—
|
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: Persian Empire representatives | Statement: [Al Khalifa family, predecessorRulersOfBahrain, Persian Empire representatives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorRulersOfBahrain Context triple: [Al Khalifa family, predecessorRulersOfBahrain, Persian Empire representatives]
-
A.
predecessorAsSultan
Indicates that one entity previously held the position of sultan before another entity, directly preceding them in that role.
-
B.
predecessorAsBuyidRulerInIraq
Indicates that one entity served as the immediately preceding Buyid ruler in Iraq relative to another entity.
-
C.
predecessorAsValideSultan
Indicates that one entity served as the immediately preceding legitimate sultan to another entity.
-
D.
successorAsBuyidRulerInIraq
Indicates that one entity became the next Buyid ruler in Iraq following another entity in succession.
-
E.
hasFormerRuler
Indicates that an entity previously served as the ruler of another entity but no longer holds that ruling position.
- F. None of above. chosen
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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138bc69d48190b185d4b8f4089922 |
completed | April 28, 2026, 10:46 p.m. |
| PD | Predicate disambiguation | batch_69e72fe1e0cc8190bd13cff2a0846225 |
completed | April 21, 2026, 8:05 a.m. |
| PDg | Predicate description generation | batch_69e7342ce08c8190bc0a7085f4a952e7 |
completed | April 21, 2026, 8:24 a.m. |
Created at: April 16, 2026, 8:39 p.m.