Triple
T16405513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AirAsia |
E398414
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
DRB-HICOM
DRB-HICOM is a major Malaysian conglomerate with diversified interests in the automotive, services, and property sectors.
|
E1212580
|
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: DRB-HICOM | Statement: [AirAsia, foundedBy, DRB-HICOM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DRB-HICOM Context triple: [AirAsia, foundedBy, DRB-HICOM]
-
A.
PDRM
PDRM is the national police force of Malaysia responsible for maintaining law and order, crime prevention, and internal security across the country.
-
B.
HIBA
HIBA is a higher education institution specializing in business administration and management studies.
-
C.
Jurong GRC
Jurong GRC is a Singaporean Group Representation Constituency in the western part of the country, known for its mix of residential, industrial, and commercial areas and representation by a multi-member team of Members of Parliament.
-
D.
Setia
Setia is the ancient Latin town that later became known as Sezze, located in the Lazio region of central Italy.
-
E.
DUN Perak
DUN Perak is the unicameral legislative body responsible for making state laws and overseeing the government in the Malaysian state of Perak.
- 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: DRB-HICOM Triple: [AirAsia, foundedBy, DRB-HICOM]
Generated description
DRB-HICOM is a major Malaysian conglomerate with diversified interests in the automotive, services, and property sectors.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: DRB-HICOM Target entity description: DRB-HICOM is a major Malaysian conglomerate with diversified interests in the automotive, services, and property sectors.
-
A.
PDRM
PDRM is the national police force of Malaysia responsible for maintaining law and order, crime prevention, and internal security across the country.
-
B.
HIBA
HIBA is a higher education institution specializing in business administration and management studies.
-
C.
Jurong GRC
Jurong GRC is a Singaporean Group Representation Constituency in the western part of the country, known for its mix of residential, industrial, and commercial areas and representation by a multi-member team of Members of Parliament.
-
D.
Setia
Setia is the ancient Latin town that later became known as Sezze, located in the Lazio region of central Italy.
-
E.
DUN Perak
DUN Perak is the unicameral legislative body responsible for making state laws and overseeing the government in the Malaysian state of Perak.
- 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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e327d2b4e48190b7153f198639e9cd |
completed | April 18, 2026, 6:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a003c62614c8190acd6d211cab1be11 |
completed | May 10, 2026, 8:05 a.m. |
| NEDg | Description generation | batch_6a003dc6f4888190ae326c9606d2a674 |
completed | May 10, 2026, 8:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0041842cc88190b81432d234f9aa17 |
completed | May 10, 2026, 8:27 a.m. |
Created at: April 10, 2026, 5:09 a.m.