Triple
T28429354
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drama Desk Award for Outstanding Actress in a Musical |
E715074
|
entity |
| Predicate | distinctionFromTonyAwards |
P18298
|
FINISHED |
| Object | includes Off-Broadway productions |
—
|
LITERAL 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: includes Off-Broadway productions | Statement: [Drama Desk Award for Outstanding Actress in a Musical, distinctionFromTonyAwards, includes Off-Broadway productions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distinctionFromTonyAwards Context triple: [Drama Desk Award for Outstanding Actress in a Musical, distinctionFromTonyAwards, includes Off-Broadway productions]
-
A.
distinctionFromOtherAwards
chosen
Indicates that one award is explicitly differentiated from or contrasted with other awards.
-
B.
hasTonyAward
Indicates that an entity has received or been awarded a Tony Award.
-
C.
numberOfTonyAwards
Indicates the total count of Tony Awards that an entity has received.
-
D.
dramaDeskAwardWinCategory
Indicates that an entity has won a Drama Desk Award in a specified award category.
-
E.
sharedTonyAwardWith
Indicates that two entities have both received a Tony Award in the same year and category, or were otherwise jointly recognized with a Tony Award.
- F. None of above.
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_69efd6b253888190b3c7222ed6a403a8 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 1:38 a.m.