Triple
T21089729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Pompeo |
E519604
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Pompeo |
—
|
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: Pompeo | Statement: [Mike Pompeo, familyName, Pompeo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pompeo Context triple: [Mike Pompeo, familyName, Pompeo]
-
A.
Mike Pompeo
chosen
Mike Pompeo is an American politician and former Director of the CIA who served as U.S. Secretary of State under President Donald Trump.
-
B.
Renda St. Clair Tillerson
Renda St. Clair Tillerson is an American businesswoman and philanthropist best known as the wife of former U.S. Secretary of State and ExxonMobil CEO Rex Tillerson.
-
C.
Mark Esper
Mark Esper is an American defense official and former U.S. Secretary of Defense who served under President Donald Trump.
-
D.
John Bolton
John Bolton is an American diplomat, lawyer, and conservative foreign policy hawk who served in senior U.S. national security roles, including as National Security Advisor under President Donald Trump.
-
E.
John Bolton
John Bolton is an American stage and television actor best known for his work in Broadway musicals and comedic roles.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b507dd9081908fb8bfcbef4c8b46 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7094dd65481909391ed74115afc23 |
completed | April 21, 2026, 5:21 a.m. |
Created at: April 16, 2026, 2:50 p.m.