Triple
T17748163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helstrom |
E443039
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Robert Wisdom |
—
|
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: Robert Wisdom | Statement: [Helstrom, leadActor, Robert Wisdom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Wisdom Context triple: [Helstrom, leadActor, Robert Wisdom]
-
A.
Robert Wisdom
chosen
Robert Wisdom is an American actor best known for his role as Major Howard "Bunny" Colvin on the television series "The Wire."
-
B.
Archie Marshek
Archie Marshek was an American film editor known for his work during Hollywood’s early sound era, including editing the 1932 thriller "The Most Dangerous Game."
-
C.
Neil Gehrels
Neil Gehrels was an influential American astrophysicist known for his pioneering work in gamma-ray astronomy and leadership of major space observatory missions.
-
D.
Tom Gehrels
Tom Gehrels was a Dutch–American astronomer known for his pioneering work in planetary science, photometry, and asteroid and comet surveys.
-
E.
George H. Dickey
George H. Dickey was an American politician after whom Dickey County in North Dakota was named.
- 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ad46a50819089c87f74efe3c7ca |
completed | April 19, 2026, 6:48 a.m. |
Created at: April 10, 2026, 10:10 a.m.