Triple

T14047204
Position Surface form Disambiguated ID Type / Status
Subject Anna University E337986 entity
Predicate hasCampus P116 FINISHED
Object ACT campus E337988 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: ACT campus | Statement: [Anna University, hasCampus, ACT campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ACT campus
Context triple: [Anna University, hasCampus, ACT campus]
  • A. ACT campus chosen
    ACT campus is one of the constituent campuses of Anna University in Tamil Nadu, India, known for its engineering and technology programs.
  • B. Campus
    Campus is a film project associated with Francesca Scorsese, known as one of her notable works in her emerging career as a filmmaker and actress.
  • C. Angel campus
    Angel campus is a central London site of City and Islington College that offers a range of further education courses and facilities for local and international students.
  • D. The Campus
    The Campus is the colloquial English name for HaKirya, the central Israel Defense Forces headquarters complex in Tel Aviv.
  • E. Campus A
    Campus A is one of the main campus locations of Airlangga University in Indonesia, hosting a range of its academic and administrative facilities.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de312df37081909f45ce3e219af5dc completed April 14, 2026, 12:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc34332448190b044f55f0f85d5e2 completed May 6, 2026, 10:40 p.m.
Created at: April 9, 2026, 10:20 p.m.