Triple

T11058163
Position Surface form Disambiguated ID Type / Status
Subject Stanford Journal of International Law E261432 entity
Predicate hasAbbreviation P43 FINISHED
Object SJIL
SJIL is a leading student-run law review at Stanford Law School that publishes scholarly articles on international and comparative law.
E902757 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: SJIL | Statement: [Stanford Journal of International Law, hasAbbreviation, SJIL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SJIL
Context triple: [Stanford Journal of International Law, hasAbbreviation, SJIL]
  • A. JSLC
    JSLC is a major Chinese spaceport in the Gobi Desert used for launching satellites and crewed Shenzhou missions into orbit.
  • B. VJIL
    VJIL is the abbreviation for the Virginia Journal of International Law, a leading student-edited law review focusing on international and comparative legal issues.
  • C. LICJ
    LICJ is the ICAO airport code for Palermo Airport, the main international gateway serving the city of Palermo in Sicily, Italy.
  • D. JLI
    JLI is the station code for Jolimont railway station, a suburban train station serving the Jolimont area of Melbourne, Australia.
  • E. .sj
    .sj is the reserved country code top-level domain designated for Svalbard and Jan Mayen, territories of Norway, which is not actively used for general internet registrations.
  • 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: SJIL
Triple: [Stanford Journal of International Law, hasAbbreviation, SJIL]
Generated description
SJIL is a leading student-run law review at Stanford Law School that publishes scholarly articles on international and comparative law.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SJIL
Target entity description: SJIL is a leading student-run law review at Stanford Law School that publishes scholarly articles on international and comparative law.
  • A. JSLC
    JSLC is a major Chinese spaceport in the Gobi Desert used for launching satellites and crewed Shenzhou missions into orbit.
  • B. VJIL
    VJIL is the abbreviation for the Virginia Journal of International Law, a leading student-edited law review focusing on international and comparative legal issues.
  • C. LICJ
    LICJ is the ICAO airport code for Palermo Airport, the main international gateway serving the city of Palermo in Sicily, Italy.
  • D. JLI
    JLI is the station code for Jolimont railway station, a suburban train station serving the Jolimont area of Melbourne, Australia.
  • E. .sj
    .sj is the reserved country code top-level domain designated for Svalbard and Jan Mayen, territories of Norway, which is not actively used for general internet registrations.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d798a2efa48190b290f43dfe836501 completed April 9, 2026, 12:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c86e0e6481908f091497313132c1 completed April 18, 2026, 6:07 p.m.
NEDg Description generation batch_69e3cefc00148190a1850dc6e31523c3 completed April 18, 2026, 6:35 p.m.
NED2 Entity disambiguation (via description) batch_69e3d014a644819092c76aa02b573ca9 completed April 18, 2026, 6:40 p.m.
Created at: April 8, 2026, 9:26 p.m.