Triple
T52040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | executive branch of the United States |
E1021
|
entity |
| Predicate | hasDeputyLeaderTitle |
P3256
|
FINISHED |
| Object | Vice President |
—
|
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: Vice President | Statement: [executive branch of the United States, hasDeputyLeaderTitle, Vice President]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDeputyLeaderTitle Context triple: [executive branch of the United States, hasDeputyLeaderTitle, Vice President]
-
A.
civilianLeaderTitle
Indicates the official title held by a person who serves as the civilian leader of a group, organization, or jurisdiction.
-
B.
hasChancellor
Indicates that an entity holds the position or role of chancellor for another entity.
-
C.
hasLeader
Indicates that one entity serves as the leader or head of another entity.
-
D.
hasLieutenantGovernor
Indicates that one entity serves as the lieutenant governor of another entity (typically a state, province, or territory).
-
E.
hasRepresentativeTitle
Indicates that an entity holds a formal title or designation that serves as its primary or most commonly used label or name.
- F. None of above. chosen
Provenance (4 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c709c248190bcd442c8d508e48c |
completed | Feb. 28, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69a24ac3c8dc819099849023bdaa35a9 |
completed | Feb. 28, 2026, 1:54 a.m. |
| PDg | Predicate description generation | batch_69a24c6ff0588190b0fd864da9aa8569 |
completed | Feb. 28, 2026, 2:01 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.