Triple
T22866040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dave Kushner |
E567055
|
entity |
| Predicate | associatedAct |
P37
|
FINISHED |
| Object | Zilch |
—
|
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: Zilch | Statement: [Dave Kushner, associatedAct, Zilch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zilch Context triple: [Dave Kushner, associatedAct, Zilch]
-
A.
Zilch
chosen
Zilch is a rock band best known as a side project of Japanese musician hide, blending alternative and industrial rock influences.
-
B.
Zer0 Sum
Zer0 Sum is the debut episode of the narrative-driven adventure game Tales from the Borderlands, introducing players to its episodic story set in the Borderlands universe.
-
C.
Sazka
Sazka is a Czech lottery and betting company that has also been a prominent sponsor of major sports and entertainment venues.
-
D.
Sacchi
Sacchi is an Italian surname most famously associated with Arrigo Sacchi, the influential former AC Milan and Italy national team football manager.
-
E.
Values of the Game
Values of the Game is a reflective book by former U.S. senator and NBA player Bill Bradley that uses basketball stories to explore character, ethics, and life lessons.
- 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f00f21081909b771610549c5757 |
completed | April 29, 2026, 3:46 a.m. |
Created at: April 17, 2026, 3:38 p.m.