Triple

T16457826
Position Surface form Disambiguated ID Type / Status
Subject Mantis E399725 entity
Predicate fightsAgainst P4567 FINISHED
Object Lord Shen E683354 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: Lord Shen | Statement: [Mantis, fightsAgainst, Lord Shen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lord Shen
Context triple: [Mantis, fightsAgainst, Lord Shen]
  • A. Lord Shen chosen
    Lord Shen is the main peacock antagonist in Kung Fu Panda 2, a ruthless and power-obsessed warlord who seeks to conquer China using deadly fireworks-based weaponry.
  • B. Lord Shang
    Lord Shang was an influential Chinese statesman and legalist reformer of the Warring States period, best known for transforming the state of Qin into a highly centralized and powerful military state.
  • C. Shenir
    Shenir is an alternate name for the Sinyar language, a Nilo-Saharan language spoken by the Sinyar people of western Sudan and eastern Chad.
  • D. Lord Anyang
    Lord Anyang was a nobleman and royal prince of the Warring States–era Zhao kingdom in ancient China, known primarily as a son of King Wuling of Zhao.
  • E. Señor Chang
    Señor Chang is the unhinged, often antagonistic Spanish teacher-turned-student from the TV series "Community," known for his erratic behavior and over-the-top antics.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32d7ef5cc819084cfeb1a3e39d3cc completed April 18, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f51d93081909ede0adcf8e604d4 completed May 10, 2026, 9:26 a.m.
Created at: April 10, 2026, 5:10 a.m.