Triple
T12463114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bob Woodward |
E297847
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Diana Woodward |
E297847
|
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: Diana Woodward | Statement: [Bob Woodward, child, Diana Woodward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Diana Woodward Context triple: [Bob Woodward, child, Diana Woodward]
-
A.
Diana Woodward
chosen
Diana Woodward is a daughter of renowned American investigative journalist Bob Woodward.
-
B.
Brenda Maddox
Brenda Maddox was an American-born British biographer and journalist renowned for her insightful literary and historical biographies, including a notable life of Nora Barnacle, James Joyce’s wife.
-
C.
Geneva Dowd
Geneva Dowd was the wife of American singer and talk show host Mike Douglas.
-
D.
Judith Myers
Judith Myers is a character in the Halloween horror franchise, known as Michael Myers' older sister and his first murder victim.
-
E.
Helen Lewis
Helen Lewis was a film editor known for her work in early American cinema, including editing the 1928 silent drama "The Docks of New York."
- 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_69d6ada270808190b1a2b2e7b02bb426 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94db5efe88190a76949e4ddc3314c |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f1f44f481909c7efdffd2aeac41 |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:56 p.m.