Triple
T11603802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Colby |
E275198
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Barbara Heinzen |
E275198
|
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: Barbara Heinzen | Statement: [William Colby, spouse, Barbara Heinzen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barbara Heinzen Context triple: [William Colby, spouse, Barbara Heinzen]
-
A.
Barbara Heinzen
chosen
Barbara Heinzen was the wife of William Colby, the former Director of Central Intelligence of the United States.
-
B.
Peggy Eisenhauer
Peggy Eisenhauer is a renowned American lighting designer known for her acclaimed work on Broadway productions and collaborations with top theater artists.
-
C.
Janice E. Voss
Janice E. Voss was an American NASA astronaut and engineer who flew on five Space Shuttle missions and contributed significantly to spaceborne scientific research and technology.
-
D.
Donna Ehlert
Donna Ehlert is best known as the first wife of American comedic actor Harvey Korman.
-
E.
Judie G. Hoyt
Judie G. Hoyt is a film producer best known for her work on the acclaimed crime drama "Mystic River."
- 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_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d895502e0081909ee9c3d45d26cd91 |
completed | April 10, 2026, 6:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f28092eb108190be203276e7dfa4b5 |
completed | April 29, 2026, 10:05 p.m. |
Created at: April 8, 2026, 9:38 p.m.