Triple

T14898706
Position Surface form Disambiguated ID Type / Status
Subject Michigan Journal of International Law E359944 entity
Predicate hasAbbreviation P43 FINISHED
Object MJIL
MJIL is a student-edited law review at the University of Michigan Law School that focuses on scholarship in international and comparative law.
E1125235 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: MJIL | Statement: [Michigan Journal of International Law, hasAbbreviation, MJIL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MJIL
Context triple: [Michigan Journal of International Law, hasAbbreviation, MJIL]
  • A. SJIL
    SJIL is a leading student-run law review at Stanford Law School that publishes scholarly articles on international and comparative law.
  • 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. MJAL
    MJAL is the ICAO airport code assigned to Jaluit Airport in the Marshall Islands.
  • D. JLI
    JLI is the station code for Jolimont railway station, a suburban train station serving the Jolimont area of Melbourne, Australia.
  • E. JSLC
    JSLC is a major Chinese spaceport in the Gobi Desert used for launching satellites and crewed Shenzhou missions into orbit.
  • 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: MJIL
Triple: [Michigan Journal of International Law, hasAbbreviation, MJIL]
Generated description
MJIL is a student-edited law review at the University of Michigan Law School that focuses on scholarship in international and comparative law.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MJIL
Target entity description: MJIL is a student-edited law review at the University of Michigan Law School that focuses on scholarship in international and comparative law.
  • A. SJIL
    SJIL is a leading student-run law review at Stanford Law School that publishes scholarly articles on international and comparative law.
  • 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. MJAL
    MJAL is the ICAO airport code assigned to Jaluit Airport in the Marshall Islands.
  • D. JLI
    JLI is the station code for Jolimont railway station, a suburban train station serving the Jolimont area of Melbourne, Australia.
  • E. JSLC
    JSLC is a major Chinese spaceport in the Gobi Desert used for launching satellites and crewed Shenzhou missions into orbit.
  • 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_69d827980cbc8190a0c569ae3940a1d9 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69ded6084574819098033a9723f3e1c4 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b6966e88190a0ed475b22a77cf1 completed May 8, 2026, 11:02 p.m.
NEDg Description generation batch_69fe6d199298819081207e27dfdf485f completed May 8, 2026, 11:09 p.m.
NED2 Entity disambiguation (via description) batch_69fe6de49480819087b36c070c434bf7 completed May 8, 2026, 11:12 p.m.
Created at: April 10, 2026, 2:11 a.m.