Triple
T32872498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theodotus of Chios |
E840828
|
entity |
| Predicate | deathOfPompeyContext |
P51826
|
FINISHED |
| Object | Pompey seeking refuge in Egypt after defeat at Pharsalus |
—
|
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: Pompey seeking refuge in Egypt after defeat at Pharsalus | Statement: [Theodotus of Chios, deathOfPompeyContext, Pompey seeking refuge in Egypt after defeat at Pharsalus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathOfPompeyContext Context triple: [Theodotus of Chios, deathOfPompeyContext, Pompey seeking refuge in Egypt after defeat at Pharsalus]
-
A.
marriageEndToPompey
Indicates that a marriage concluded or was terminated in relation to Pompey (e.g., by divorce, annulment, or death).
-
B.
SullaDictatorshipEnd
Indicates that the event marks the conclusion or termination of Sulla’s period of dictatorship.
-
C.
containsDeathOf
chosen
Indicates that the subject includes, depicts, or involves the death of the referenced entity.
-
D.
reignAsCaesarEnd
Indicates the time or event at which an individual’s tenure or rule as Caesar comes to an end.
-
E.
emperorKilled
Indicates that an emperor caused the death of another entity.
- 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_69f349436ee88190b72ee12d0f3f508e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f739a638748190808e7a2930dce16e |
completed | May 3, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f732f2dc6c8190a4e86da98cc5eb05 |
completed | May 3, 2026, 11:35 a.m. |
Created at: May 1, 2026, 1:17 a.m.