Triple
T3153919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gabrielle Union |
E65939
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Top Five |
E247199
|
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: Top Five | Statement: [Gabrielle Union, notableWork, Top Five]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Top Five Context triple: [Gabrielle Union, notableWork, Top Five]
-
A.
Top Five
chosen
Top Five is a 2014 comedy film written, directed by, and starring Chris Rock, following a comedian’s struggle to reinvent his career while navigating fame and relationships.
-
B.
At the Top
At the Top is the Burj Khalifa’s main public observation experience, offering panoramic views of Dubai from some of the world’s highest viewing platforms.
-
C.
On Top
"On Top" is a 1966 studio album by Motown vocal group the Four Tops, showcasing their soulful harmonies and classic Detroit sound.
-
D.
Top 14
Top 14 is the premier professional rugby union league in France, featuring the country’s top clubs and many of the world’s best players.
-
E.
Today’s Top 10 Award
Today’s Top 10 Award is a prestigious NCAA honor recognizing outstanding student-athletes who excel in athletics, academics, and leadership.
- 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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5e7f4688190b477186254f8a572 |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b22503ba208190814ab2bfbe380c42 |
completed | March 12, 2026, 2:29 a.m. |
Created at: March 8, 2026, 3:05 p.m.