Triple
T14413233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Covenant |
E357382
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Taylor Kitsch |
E342944
|
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: Taylor Kitsch | Statement: [The Covenant, castMember, Taylor Kitsch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taylor Kitsch Context triple: [The Covenant, castMember, Taylor Kitsch]
-
A.
Taylor Kitsch
chosen
Taylor Kitsch is a Canadian actor best known for his breakout role as Tim Riggins on the television series "Friday Night Lights" and for starring in films such as "John Carter" and "Lone Survivor."
-
B.
Steve Kinnaman
Steve Kinnaman is the father of Swedish-American actor Joel Kinnaman.
-
C.
Garrett Hedlund
Garrett Hedlund is an American actor and singer known for roles in films such as "Tron: Legacy," "Friday Night Lights," and "Country Strong."
-
D.
Thomas Roy Skerritt
Thomas Roy Skerritt is an American actor best known for his roles in films such as "M*A*S*H," "Alien," and "Top Gun," as well as the television series "Picket Fences."
-
E.
James Marsden
James Marsden is an American actor known for his roles in films like the X-Men series, Enchanted, and Hairspray, as well as prominent television work.
- 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de90cb3c708190822f5506ebf7ee9d |
completed | April 14, 2026, 7:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd552858208190ba1550e7c1176a2a |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:17 a.m.