Triple
T29868512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julii Caesares |
E758521
|
entity |
| Predicate | bestKnownMember |
P145741
|
FINISHED |
| Object | Gaius Julius Caesar |
—
|
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: Gaius Julius Caesar | Statement: [Julii Caesares, bestKnownMember, Gaius Julius Caesar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestKnownMember Context triple: [Julii Caesares, bestKnownMember, Gaius Julius Caesar]
-
A.
bestKnownSingle
Indicates that the referenced item is the most prominent or widely recognized single associated with an entity (such as an artist or group).
-
B.
bestKnownRepresentative
chosen
Indicates that one entity is regarded as the most prominent or widely recognized example or representative of another entity.
-
C.
lastKnownMember
Indicates that the subject is the most recent or final identified member of a particular group, lineage, or set.
-
D.
largestKnownMembers
Indicates that the related entities are the largest known members within a specified group, category, or set.
-
E.
bestKnownStructure
Indicates that the related entity is the most prominent or widely recognized structure associated with the subject.
- 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_69f2245d0d7081909e37ee328542bcd7 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6768b2bf48190af4821d43d7ee766 |
completed | May 2, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:52 p.m.