Triple
T28738853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batman and Harley Quinn |
E730879
|
entity |
| Predicate | characterVoicedBy Kevin Conroy |
P191789
|
FINISHED |
| Object | Batman |
—
|
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: Batman | Statement: [Batman and Harley Quinn, characterVoicedBy Kevin Conroy, Batman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterVoicedBy Kevin Conroy Context triple: [Batman and Harley Quinn, characterVoicedBy Kevin Conroy, Batman]
-
A.
voiceActorOfAlfredPennyworth
Indicates that the subject is a voice actor who provides the voice for the character Alfred Pennyworth.
-
B.
roleInBatmanAndRobin
Indicates that an entity has a specific role or involvement in the context of "Batman and Robin" (such as the story, franchise, or related work).
-
C.
voiceActorForSuperman
Indicates that one entity serves as the voice actor portraying the character Superman in a performance or production.
-
D.
voiceActorOfTheJoker
Indicates that one entity is the voice actor who provides the voice for the character "The Joker" in a given production or context.
-
E.
characterVoicedBy Ashton Kutcher
Indicates that a character is voiced by Ashton Kutcher in a performance or production.
- F. None of above. chosen
Provenance (4 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_69f043eae0908190b28ce314686247d7 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
| PDg | Predicate description generation | batch_69fcec5e560481909cd710b88897e833 |
completed | May 7, 2026, 7:47 p.m. |
Created at: April 28, 2026, 6:02 a.m.