Triple
T18334349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Tasker |
E439229
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Dana Tasker |
—
|
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: Dana Tasker | Statement: [Harry Tasker, child, Dana Tasker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dana Tasker Context triple: [Harry Tasker, child, Dana Tasker]
-
A.
Dana Tasker
chosen
Dana Tasker is the teenage daughter of secret agent Harry Tasker in the action-comedy film "True Lies."
-
B.
Renee Olstead
Renee Olstead is an American actress and jazz-influenced pop singer known for her rich, soulful vocals and roles in television series such as "Still Standing" and "The Secret Life of the American Teenager."
-
C.
Dana Congdon
Dana Congdon is a film editor best known for his work on movies such as the anthology comedy "Four Rooms."
-
D.
Denise Huth
Denise Huth is a television producer best known for her long-running work as an executive producer on AMC’s The Walking Dead franchise and its related spin-offs.
-
E.
Danelle Morton
Danelle Morton is an American journalist and author known for co-writing celebrity memoirs and nonfiction books, including collaborating with Lynne Spears.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecc91148190aa820fcd466009ce |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:36 a.m.