Triple
T19137042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Dougherty |
E468459
|
entity |
| Predicate | collaboratesWith |
P37
|
FINISHED |
| Object | Zach Shields |
—
|
NE NERFINISHED |
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: Zach Shields | Statement: [Michael Dougherty, collaboratesWith, Zach Shields]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zach Shields Context triple: [Michael Dougherty, collaboratesWith, Zach Shields]
-
A.
Zach Shields
Zach Shields is an American screenwriter and filmmaker known for co-writing major monster movies such as "Godzilla vs. Kong."
-
B.
Zach Shields
chosen
Zach Shields is a screenwriter and filmmaker best known for co-writing the holiday horror-comedy film "Krampus" (2015), often collaborating with director Michael Dougherty.
-
C.
Zach Nunn
Zach Nunn is a Republican U.S. Representative from Iowa who serves as part of the state’s congressional delegation.
-
D.
Ryan Binkley
Ryan Binkley is an American pastor and businessman who ran as a long-shot candidate in the 2024 Republican presidential primaries.
-
E.
Zach McGowan
Zach McGowan is an American actor known for his rugged roles in television series like "Shameless," "Black Sails," and "The 100," as well as various film appearances.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3edd1c48190b86bef530ebbd092 |
completed | April 20, 2026, 8:29 a.m. |
Created at: April 10, 2026, 12:05 p.m.