Triple
T10367789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Human Traffic |
E244299
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Justin Kerrigan |
E860611
|
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: Justin Kerrigan | Statement: [Human Traffic, director, Justin Kerrigan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Justin Kerrigan Context triple: [Human Traffic, director, Justin Kerrigan]
-
A.
Justin Kerrigan
chosen
Justin Kerrigan is a Welsh filmmaker best known for writing and directing the 1999 cult club-culture film "Human Traffic."
-
B.
Bryan Zuriff
Bryan Zuriff is a television producer best known for his work as an executive producer on the crime drama series "Ray Donovan."
-
C.
Alex Seidel
Alex Seidel was a German firearms designer and industrialist best known as one of the co-founders of the weapons manufacturer Heckler & Koch.
-
D.
Kyle Macy
Kyle Macy is a former American college basketball star and NBA guard best known for his standout career at the University of Kentucky in the late 1970s.
-
E.
Dane Krager
Dane Krager is an American indoor football executive and former player who serves as the general manager of the Frisco Fighters in the Indoor Football League.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e97106448190a075948e63184f47 |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87e64109881908c42a4fbcfd057be |
completed | April 10, 2026, 4:36 a.m. |
Created at: April 6, 2026, noon