Triple
T36621593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanzanian road network |
E904052
|
entity |
| Predicate | hasPolicyMaker |
P169275
|
FINISHED |
| Object | Government of Tanzania |
—
|
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: Government of Tanzania | Statement: [Tanzanian road network, hasPolicyMaker, Government of Tanzania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPolicyMaker Context triple: [Tanzanian road network, hasPolicyMaker, Government of Tanzania]
-
A.
hasDecisionMaker
Indicates that one entity serves as the decision-making authority or agent for another entity.
-
B.
policyMaker
chosen
Indicates that an entity plays a role in creating, shaping, or deciding policies that govern or guide others.
-
C.
hasDecisionMakingPower
Indicates that one entity possesses the authority or ability to make decisions that affect another entity or a given context.
-
D.
hasPolicyGoal
Indicates that an entity is associated with, or aims to achieve, a specific policy objective or target.
-
E.
hasPolicyIssue
Indicates that an entity is associated with a specific policy-related problem, concern, or noncompliance.
- 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_69f76e6ae750819096911e6e2d4d12c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff8ba3f8248190bbdf8e7ec2b35093 |
completed | May 9, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69ff8b41ba988190a7332e8317d10f09 |
completed | May 9, 2026, 7:30 p.m. |
Created at: May 3, 2026, 4:11 p.m.