Triple

T7846984
Position Surface form Disambiguated ID Type / Status
Subject Office of Sanctions Policy and Implementation E181947 entity
Predicate hasAbbreviation P43 FINISHED
Object SPI
SPI is the Office of Sanctions Policy and Implementation, a U.S. State Department office responsible for developing and coordinating economic sanctions policy.
 E698609 NE FINISHED

How this triple was built (4 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: SPI | Statement: [Office of Sanctions Policy and Implementation, hasAbbreviation, SPI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SPI
Context triple: [Office of Sanctions Policy and Implementation, hasAbbreviation, SPI]
  • A. SPI
    SPI is a stock market index that includes companies such as SIX:NESN and tracks the performance of the broader Swiss equity market.
  • B. SPI
    SPI is the IATA airport code for Abraham Lincoln Capital Airport serving Springfield, Illinois, in the United States.
  • C. I2C
    I2C is a widely used two-wire serial communication bus that enables simple, low-speed data exchange between microcontrollers and peripheral devices on the same circuit board.
  • D. MOSI
    MOSI is a major science and technology museum known for its interactive exhibits and educational programs that promote public engagement with science and industry.
  • E. SPICE
    SPICE is Amazon QuickSight’s in-memory calculation and storage engine designed to enable fast, scalable, and interactive data analysis.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SPI
Triple: [Office of Sanctions Policy and Implementation, hasAbbreviation, SPI]
Generated description
SPI is the Office of Sanctions Policy and Implementation, a U.S. State Department office responsible for developing and coordinating economic sanctions policy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SPI
Target entity description: SPI is the Office of Sanctions Policy and Implementation, a U.S. State Department office responsible for developing and coordinating economic sanctions policy.
  • A. SPI
    SPI is the IATA airport code for Abraham Lincoln Capital Airport serving Springfield, Illinois, in the United States.
  • B. SPI
    SPI is a stock market index that includes companies such as SIX:NESN and tracks the performance of the broader Swiss equity market.
  • C. I2C
    I2C is a widely used two-wire serial communication bus that enables simple, low-speed data exchange between microcontrollers and peripheral devices on the same circuit board.
  • D. MOSI
    MOSI is a major science and technology museum known for its interactive exhibits and educational programs that promote public engagement with science and industry.
  • E. SPICE
    SPICE is Amazon QuickSight’s in-memory calculation and storage engine designed to enable fast, scalable, and interactive data analysis.
  • F. None of above. chosen

Provenance (5 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_69ca8285d6488190a95d4c02d7354b53 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb164105fc8190a60aaa27dd619d5a completed March 31, 2026, 12:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5af27c9c8190a3e6062d323acff1 completed March 31, 2026, 5:26 a.m.
NEDg Description generation batch_69cb5def38e88190864d84abd7959aa3 completed March 31, 2026, 5:38 a.m.
NED2 Entity disambiguation (via description) batch_69cb766e41fc8190a08f07d04774053a completed March 31, 2026, 7:23 a.m.
Created at: March 30, 2026, 4:49 p.m.