Triple
T20901071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teen Titans: The Judas Contract (film) |
E514667
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Terra (Tara Markov) |
—
|
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: Terra (Tara Markov) | Statement: [Teen Titans: The Judas Contract (film), featuresCharacter, Terra (Tara Markov)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terra (Tara Markov) Context triple: [Teen Titans: The Judas Contract (film), featuresCharacter, Terra (Tara Markov)]
-
A.
Tara Markov
chosen
Tara Markov is a DC Comics character better known as Terra, a troubled teenage metahuman with powerful earth-manipulation abilities and a complex history with the Teen Titans.
-
B.
Kaela Tucker
Kaela Tucker is a member of the Tucker family, known publicly as the sister of Ace Wells Tucker, the son of reality TV star Kandi Burruss and producer Todd Tucker.
-
C.
Tasha
Tasha is a common given name, often used as a diminutive of Natasha.
-
D.
Xandra
Xandra is a shortened, informal given name derived from Alexandra, often used as a modern, distinctive feminine name.
-
E.
Kaela
Kaela is the given name of American professional basketball player Kaela Davis.
- 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8fc5d488190b62f51c35e768d38 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.