Triple
T16941606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bureau of Investigation of the Republic of China |
E410961
|
entity |
| Predicate | commonName |
P570
|
FINISHED |
| Object |
MJIB
MJIB is Taiwan’s national investigative and intelligence agency responsible for counterintelligence, security, and major criminal investigations.
|
E1242001
|
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: MJIB | Statement: [Bureau of Investigation of the Republic of China, commonName, MJIB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MJIB Context triple: [Bureau of Investigation of the Republic of China, commonName, MJIB]
-
A.
JIB
JIB is the IATA airport code for Djibouti–Ambouli International Airport, the main international gateway serving Djibouti.
-
B.
MBJ
MBJ is the IATA airport code for Sangster International Airport, the main tourist gateway serving Montego Bay, Jamaica.
-
C.
MJ
MJ is a Master of Jurisprudence graduate law degree designed for non-lawyers seeking advanced legal knowledge in a specific field.
-
D.
MJ
MJ is the widely used nickname for Michael Jordan, the legendary American basketball player often regarded as the greatest in NBA history.
-
E.
MJ
MJ is a reimagined version of the Mary Jane Watson character who appears as Peter Parker’s sharp, observant classmate and love interest in the Marvel Cinematic Universe Spider-Man films.
- 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: MJIB Triple: [Bureau of Investigation of the Republic of China, commonName, MJIB]
Generated description
MJIB is Taiwan’s national investigative and intelligence agency responsible for counterintelligence, security, and major criminal investigations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MJIB Target entity description: MJIB is Taiwan’s national investigative and intelligence agency responsible for counterintelligence, security, and major criminal investigations.
-
A.
JIB
JIB is the IATA airport code for Djibouti–Ambouli International Airport, the main international gateway serving Djibouti.
-
B.
MBJ
MBJ is the IATA airport code for Sangster International Airport, the main tourist gateway serving Montego Bay, Jamaica.
-
C.
MJ
MJ is the widely used nickname for Michael Jordan, the legendary American basketball player often regarded as the greatest in NBA history.
-
D.
MJ
MJ is a reimagined version of the Mary Jane Watson character who appears as Peter Parker’s sharp, observant classmate and love interest in the Marvel Cinematic Universe Spider-Man films.
-
E.
MJ
MJ is a Master of Jurisprudence graduate law degree designed for non-lawyers seeking advanced legal knowledge in a specific field.
- 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_69d886c886688190967be07322597ac9 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cfadec70819095ec0048ebc71016 |
completed | April 18, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfea3bc88190acaa013169d607c5 |
completed | May 10, 2026, 6:35 p.m. |
| NEDg | Description generation | batch_6a00d0b13f1c819091f3f8b966e36214 |
completed | May 10, 2026, 6:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00d1ad6b7081908be76d70ad9e2075 |
completed | May 10, 2026, 6:42 p.m. |
Created at: April 10, 2026, 5:31 a.m.