Triple
T15361876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cleitus the Black saved Alexander's life |
E367306
|
entity |
| Predicate | CleitusRole |
P40371
|
FINISHED |
| Object | Macedonian officer |
—
|
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: Macedonian officer | Statement: [Cleitus the Black saved Alexander's life, CleitusRole, Macedonian officer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: CleitusRole Context triple: [Cleitus the Black saved Alexander's life, CleitusRole, Macedonian officer]
-
A.
CorwinRole
Indicates that an entity holds or is assigned a specific role or function in relation to Corwin.
-
B.
RexRole
Indicates a role or function that an entity holds within a specific context, system, or structure.
-
C.
unitRole
chosen
Indicates the functional role or purpose that a unit serves within a larger system or context.
-
D.
roleInTauris
Indicates that an entity has a specific role or function within the context of Tauris (e.g., a work, setting, or domain associated with Tauris).
-
E.
sonRole
Indicates that one entity holds the role or relationship of a son with respect to 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_69d85a1483788190ad93c2748e8af34b |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e479f188190bbbc3dcd73853e02 |
completed | April 16, 2026, 1:41 a.m. |
| PD | Predicate disambiguation | batch_69deca991e5081908b0df3d1ee7d5338 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:18 a.m.