Triple
T2151981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onward |
E47799
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Julia Louis-Dreyfus |
E12701
|
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: Julia Louis-Dreyfus | Statement: [Onward, voiceActor, Julia Louis-Dreyfus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julia Louis-Dreyfus Context triple: [Onward, voiceActor, Julia Louis-Dreyfus]
-
A.
Julia Louis-Dreyfus
chosen
Julia Louis-Dreyfus is an American actress and comedian best known for her iconic roles on the television series "Seinfeld" and "Veep."
-
B.
Allison Janney
Allison Janney is an American actress acclaimed for her Emmy-winning portrayal of press secretary C.J. Cregg on the political drama series "The West Wing."
-
C.
Debra Messing
Debra Messing is an American actress best known for her Emmy-winning role as Grace Adler on the sitcom "Will & Grace."
-
D.
Amy Poehler
Amy Poehler is an American comedian, actress, writer, and producer best known for her work on "Saturday Night Live" and for starring as Leslie Knope on the sitcom "Parks and Recreation."
-
E.
Phyllis Smith
Phyllis Smith is an American actress best known for playing the soft-spoken saleswoman Phyllis Vance on the U.S. version of the television series "The Office."
- 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_69a88a1d1fd8819088b34990d69a712f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe48ad148190a7d6cc88fd38a660 |
completed | March 7, 2026, 5:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58e0e1b481909545e8e6d861adfd |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:44 p.m.