Triple

T8391504
Position Surface form Disambiguated ID Type / Status
Subject Ben Cross E197952 entity
Predicate appearedIn P795 FINISHED
Object Banshee E618112 NE 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: Banshee | Statement: [Ben Cross, appearedIn, Banshee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banshee
Context triple: [Ben Cross, appearedIn, Banshee]
  • A. Banshee chosen
    Banshee is an American action-drama television series known for its violent, stylized storytelling about an ex-con assuming a dead sheriff’s identity in a small Amish-country town.
  • B. Wraith
    Wraith is a horror comic series by Joe Hill that expands on the sinister world and characters of his novel "NOS4A2."
  • C. Wraith
    The Wraith are a vampiric, hive-based alien species in Stargate Atlantis who feed on human life-force and serve as the show's primary recurring antagonists.
  • D. Raven
    Raven is a powerful, empathic half-demon sorceress and core member of the Teen Titans, known for her dark, reserved personality and struggle to control her immense magical abilities.
  • E. Raven
    Raven is a central trickster-creator figure in Haida mythology, known for shaping the world and bringing light and knowledge to humanity.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb810e16b081908e2c25bfb9d590ed completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde84d6f3c8190ba12905ba5900087 completed April 2, 2026, 3:53 a.m.
Created at: March 30, 2026, 6:03 p.m.