Triple
T30201940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | True Whig Party |
E767802
|
entity |
| Predicate | controlledBranch |
P52072
|
FINISHED |
| Object | executive branch of Liberia |
—
|
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: executive branch of Liberia | Statement: [True Whig Party, controlledBranch, executive branch of Liberia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlledBranch Context triple: [True Whig Party, controlledBranch, executive branch of Liberia]
-
A.
trainedBranch
Indicates that one entity has provided training or instruction to a specific branch or subdivision of another entity.
-
B.
possibleBranch
Indicates that one entity can serve as an alternative or potential continuation path branching from another entity.
-
C.
commandedBranch
chosen
Indicates that one entity held command authority over a particular branch, unit, or subdivision of an organization.
-
D.
representedBranch
Indicates that one entity serves as a representative or proxy for a particular branch of another entity or organization.
-
E.
addressedBranch
Indicates that an action, communication, or item is specifically directed to or associated with a particular branch of an organization or network.
- 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_69f2247db1108190835c0727c97637c3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: April 29, 2026, 7:30 p.m.