Triple
T4379373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gracie |
E99089
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Gracie Gold |
E267367
|
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: Gracie Gold | Statement: [Gracie, hasNotableBearer, Gracie Gold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gracie Gold Context triple: [Gracie, hasNotableBearer, Gracie Gold]
-
A.
Gracie Gold
chosen
Gracie Gold is an American figure skater known for being a U.S. national champion and competing in the 2014 Winter Olympics.
-
B.
Jamie Linden
Jamie Linden is an American screenwriter and film director known for writing movies such as "We Are Marshall," "Dear John," and the financial thriller "Money Monster."
-
C.
Tiler Peck
Tiler Peck is an acclaimed American ballet dancer and principal with New York City Ballet, renowned for her musicality, speed, and versatility in both classical and contemporary roles.
-
D.
Sarah Hughes
Sarah Hughes is an American figure skater best known for winning the ladies' singles gold medal at the 2002 Winter Olympics.
-
E.
Valerie Velardi
Valerie Velardi is an American actress and dancer best known as the first wife of comedian and actor Robin Williams.
- 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_69b3454ea8f48190a49c2436624d6ef6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3524154dc81908532cdf997dcb802 |
completed | March 12, 2026, 11:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e51c87908190a561513ec64a2d72 |
completed | March 14, 2026, 10:45 p.m. |
Created at: March 12, 2026, 11:18 p.m.