Triple
T28847403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antigonus the One-Eyed |
E728489
|
entity |
| Predicate | successorAsKingInAsia |
P86701
|
FINISHED |
| Object | Seleucus I Nicator |
—
|
NE NERFINISHED |
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: Seleucus I Nicator | Statement: [Antigonus the One-Eyed, successorAsKingInAsia, Seleucus I Nicator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorAsKingInAsia Context triple: [Antigonus the One-Eyed, successorAsKingInAsia, Seleucus I Nicator]
-
A.
successorAsEasternRuler
chosen
Indicates that one entity became the next ruler of an eastern domain or territory after another entity.
-
B.
successorInJapan
Indicates that one entity directly follows or replaces another in a role, position, or sequence within the context of Japan.
-
C.
successorInChina
Indicates that one entity directly follows or replaces another in a position, role, or sequence within the context of China.
-
D.
successorAsDeFactoRuler
Indicates that one entity becomes the next actual (though not necessarily officially recognized) ruler after another entity.
-
E.
successorSovereign
Indicates that one entity becomes the next ruling sovereign following another entity, inheriting their position of supreme authority.
- 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_69f0319e8e7c8190b37288c8845b9dbc |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69fdbaa226708190b8ed96e93aad38de |
completed | May 8, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69fdb58b07e48190837e00966de050d4 |
completed | May 8, 2026, 10:06 a.m. |
Created at: April 28, 2026, 6:42 a.m.