Triple
T34058199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pastoral period |
E873418
|
entity |
| Predicate | influencesResearchOn |
P173356
|
FINISHED |
| Object | origins of pastoralism in Africa |
—
|
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: origins of pastoralism in Africa | Statement: [Pastoral period, influencesResearchOn, origins of pastoralism in Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: influencesResearchOn Context triple: [Pastoral period, influencesResearchOn, origins of pastoralism in Africa]
-
A.
influencedScholar
Indicates that one scholar has had a significant intellectual or academic impact on another scholar’s work, ideas, or development.
-
B.
influencesThrough
Indicates that one entity affects or alters another entity indirectly by means of an intermediate factor, channel, or mechanism.
-
C.
exploresInfluence
Indicates that one entity investigates, examines, or analyzes the impact or effect that another entity has.
-
D.
influencesFocus
Indicates that one entity affects or shapes the attention, concentration, or focal priorities of another entity.
-
E.
influenceOf
chosen
Indicates that one entity affects, shapes, or alters the state, behavior, or properties 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_69f349a4af208190afa14888f9c9fb9d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
Created at: May 1, 2026, 1:52 a.m.