Triple
T16457573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 50/50 |
E399720
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Andrew Airlie |
E1027897
|
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: Andrew Airlie | Statement: [50/50, starring, Andrew Airlie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Airlie Context triple: [50/50, starring, Andrew Airlie]
-
A.
Andrew Airlie
chosen
Andrew Airlie is a Canadian actor known for his work in film and television, including roles in series like "Reaper" and the "Fifty Shades" film franchise.
-
B.
Daniel Ralls
Daniel Ralls was an early 19th-century Missouri legislator and local political figure after whom Ralls County, Missouri, is named.
-
C.
Bruce Davey
Bruce Davey is an Australian film producer best known for his long-time collaboration with Mel Gibson and for co-founding the production company Icon Productions.
-
D.
Andy Hertzfeld
Andy Hertzfeld is a pioneering software engineer best known as a key member of the original Apple Macintosh development team and a co-creator of the Mac’s graphical user interface.
-
E.
Andrew Tridgell
Andrew Tridgell is an Australian computer programmer best known for creating the Samba software suite and contributing extensively to free and open-source software.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32d7ef5cc819084cfeb1a3e39d3cc |
completed | April 18, 2026, 7:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f51d93081909ede0adcf8e604d4 |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:10 a.m.