Triple
T21744288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Kelly |
E536743
|
entity |
| Predicate | exSpouse |
P23411
|
FINISHED |
| Object | Laura Kelly |
—
|
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: Laura Kelly | Statement: [John Kelly, exSpouse, Laura Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Kelly Context triple: [John Kelly, exSpouse, Laura Kelly]
-
A.
Laura Kelly
Laura Kelly is an American Democratic politician serving as the governor of Kansas.
-
B.
Laura Kelly
Laura Kelly is the ambitious young attorney portrayed by Debra Winger in the 1986 legal comedy-drama film "Legal Eagles."
-
C.
Terri Flores
Terri Flores is the resourceful documentary filmmaker and protagonist portrayed by Jennifer Lopez in the 1997 horror-adventure film "Anaconda."
-
D.
Lupe Valdez
Lupe Valdez is an American politician and former Dallas County sheriff who became the Democratic nominee for governor of Texas in 2018.
-
E.
Julia Carin Cavazos
Julia Carin Cavazos, known professionally as Julia Michaels, is an American singer-songwriter recognized for her solo pop hits and for writing chart-topping songs for numerous major artists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a75352c8190bcd46759562ee251 |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 16, 2026, 6:49 p.m.