Triple
T23111112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christina Vidal |
E576320
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Lisa Vidal |
—
|
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: Lisa Vidal | Statement: [Christina Vidal, sibling, Lisa Vidal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Vidal Context triple: [Christina Vidal, sibling, Lisa Vidal]
-
A.
Lisa Vidal
chosen
Lisa Vidal is an American actress known for her work in television dramas and films, including prominent roles in series like "The Division," "ER," and "Being Mary Jane."
-
B.
Vickie Castro
Vickie Castro is a Chicana activist and educator known for her leadership role in the 1968 East Los Angeles student walkouts for educational reform.
-
C.
Marian Quinn
Marian Quinn is an Irish filmmaker and actress known for writing and directing the independent film "32A."
-
D.
Emily Sullivan
Emily Sullivan is a fictional character from the science fiction television series "Jericho," portrayed by actress Ashley Scott.
-
E.
Martine Bartlett
Martine Bartlett was an American character actress known for her intense and often emotionally complex roles in film and television during the mid-20th century.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0f4d188190a9395074c630ab0d |
completed | April 29, 2026, 4:50 a.m. |
Created at: April 17, 2026, 3:58 p.m.