Triple
T11183530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsha Garces |
E264601
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Zelda Williams |
E248337
|
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: Zelda Williams | Statement: [Marsha Garces, child, Zelda Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zelda Williams Context triple: [Marsha Garces, child, Zelda Williams]
-
A.
Zelda Williams
chosen
Zelda Williams is an American actress, voice artist, and director, and the daughter of the late comedian and actor Robin Williams.
-
B.
Zelda Harris
Zelda Harris is an American actress best known for her childhood roles in films such as Spike Lee’s "Crooklyn" and the basketball drama "He Got Game."
-
C.
Zelda Sayre
Zelda Sayre was an American socialite, writer, and painter best known as the flamboyant wife and muse of novelist F. Scott Fitzgerald and a symbol of the Jazz Age.
-
D.
Zelda Gilroy
Zelda Gilroy is a brainy, persistent, and lovelorn high school girl who relentlessly pursues Dobie in the classic American sitcom "The Many Loves of Dobie Gillis."
-
E.
Kealia Ohai
Kealia Ohai is an American professional soccer forward known for her standout NWSL career and leadership with the Houston Dash.
- 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_69d6aa9dafac8190bd90d2c74f661aa7 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8a9c5e081908c85b41a268428fb |
completed | April 9, 2026, 5:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e483c1b4f88190b7c38b254d37c7fb |
completed | April 19, 2026, 7:26 a.m. |
Created at: April 8, 2026, 9:29 p.m.