Triple

T15217826
Position Surface form Disambiguated ID Type / Status
Subject SIGACT E363684 entity
Predicate affiliation P10 FINISHED
Object ACM E294926 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: ACM | Statement: [SIGACT, affiliation, ACM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ACM
Context triple: [SIGACT, affiliation, ACM]
  • A. ACM chosen
    ACM is a leading international scientific and educational computing society known for publishing research journals, organizing conferences, and advancing the field of computer science.
  • B. ACM
    ACM is the stock ticker symbol for AECOM, a global infrastructure consulting and engineering firm.
  • C. ACM
    ACM is the commonly used abbreviation for the Appellate Court of Maryland, an intermediate appellate court in the Maryland state judiciary.
  • D. ACM
    ACM is an abbreviation commonly used to refer to Alarm Communication Management, a system or framework for handling and coordinating alarm-related communications.
  • E. ACM
    ACM is a senior four-star air officer rank used in several air forces, typically held by the professional head of the service.
  • 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_69d85a0ce24c81909c4d3b6475548c95 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0076f90c481909989befe031a2cae completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fed343f51481908f04c35d37b39ad2 completed May 9, 2026, 6:25 a.m.
Created at: April 10, 2026, 3:11 a.m.