Triple
T17747918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rossum Corporation |
E443034
|
entity |
| Predicate | employs |
P7
|
FINISHED |
| Object | Paul Ballard |
—
|
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: Paul Ballard | Statement: [Rossum Corporation, employs, Paul Ballard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Ballard Context triple: [Rossum Corporation, employs, Paul Ballard]
-
A.
Paul Ballard
chosen
Paul Ballard is a determined FBI agent in the television series "Dollhouse" who becomes obsessed with uncovering the truth behind the mysterious Dollhouse organization.
-
B.
Russ Ballard
Russ Ballard is an English singer, songwriter, and musician best known for writing hit songs for artists like Argent, Rainbow, and Kiss, as well as for his own solo work.
-
C.
Paul Bowen
Paul Bowen is a British aviation enthusiast and organizer best known for co-founding and developing the Royal International Air Tattoo into one of the world’s largest military airshows.
-
D.
Sam Ball
Sam Ball is an actor known for his supporting role in the romantic comedy film "13 Going on 30."
-
E.
James William Ballard
James William Ballard is an actor known for appearing in the action film "Expend4bles."
- 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_69e47ad33160819093c9bbd3c8957314 |
completed | April 19, 2026, 6:48 a.m. |
Created at: April 10, 2026, 10:10 a.m.