Triple
T14126644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savannah Guthrie |
E340049
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | CourtTV |
E22490
|
NE 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: CourtTV | Statement: [Savannah Guthrie, employer, CourtTV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CourtTV Context triple: [Savannah Guthrie, employer, CourtTV]
-
A.
Court TV
chosen
Court TV is a U.S. television network focused on live trial coverage and legal-themed programming.
-
B.
Court
Court is a critically acclaimed Marathi-language courtroom drama film that explores the injustices and bureaucratic absurdities of the Indian legal system.
-
C.
Court
Court is a common English surname of Norman origin, often associated with families historically linked to manorial courts or residences.
-
D.
People's Court
The People's Court was a notorious Nazi special court in Germany that conducted highly politicized show trials and handed down numerous death sentences, particularly against political opponents and resistance members.
-
E.
Tribunal
Tribunal is a station on the Madrid Metro located in the central district of the city, serving as an important interchange between multiple metro lines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de6096976481909dc79066c5165a50 |
completed | April 14, 2026, 3:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdf0c833081908458e4eaee689df7 |
completed | May 7, 2026, 6:50 p.m. |
Created at: April 9, 2026, 10:22 p.m.