Triple
T7377882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Davis |
E170171
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Mark Davis |
E158148
|
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: Mark Davis | Statement: [Al Davis, child, Mark Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Davis Context triple: [Al Davis, child, Mark Davis]
-
A.
Mark Davis
Mark Davis is a computer scientist and software engineer best known for co-founding the Unicode Consortium and helping to design and standardize the Unicode character encoding system.
-
B.
Mark Davis
chosen
Mark Davis is an American businessman best known as the principal owner of the NFL’s Las Vegas Raiders and the WNBA’s Las Vegas Aces.
-
C.
John Whitesell
John Whitesell is an American television and film director and producer known for his work on various TV series and feature comedies.
-
D.
Larry Davis
Larry Davis is best known as a former husband of actress Kim Cattrall.
-
E.
Don Davis
Don Davis is an American composer best known for his innovative, genre-defining film scores for The Matrix trilogy.
- 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_69c68a5bfaac81909ce7f001dfb70c76 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1aa12888190b81e37b9fcd2adc0 |
completed | March 27, 2026, 9:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802d57ae88190840442621d8bef35 |
completed | March 28, 2026, 4:33 p.m. |
Created at: March 27, 2026, 3:08 p.m.