Triple
T23215452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbara Marshall |
E580724
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Kathleen Marshall |
—
|
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: Kathleen Marshall | Statement: [Barbara Marshall, hasChild, Kathleen Marshall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kathleen Marshall Context triple: [Barbara Marshall, hasChild, Kathleen Marshall]
-
A.
Kathleen Marshall
Kathleen Marshall is an American television director and producer known for her work on series such as "The Odd Couple" and "Fuller House."
-
B.
Kathleen Marshall
chosen
Kathleen Marshall is an American theatre director and choreographer known for her acclaimed work on Broadway musicals and multiple Tony Award wins.
-
C.
Sandy Powell
Sandy Powell is a renowned British costume designer celebrated for her innovative and influential work on numerous acclaimed films.
-
D.
Jocelyn Moorhouse
Jocelyn Moorhouse is an Australian film director and screenwriter known for character-driven dramas such as "Proof" and "How to Make an American Quilt."
-
E.
Kasi Lemmons
Kasi Lemmons is an American film director, screenwriter, and actress known for works such as "Eve's Bayou," "Harriet," and other character-driven dramas exploring African American experiences.
- 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f191646c548190a3f7150f0c253dc1 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:08 p.m.