Triple
T13914880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HNA Group |
E334594
|
entity |
| Predicate | keyPerson |
P256
|
FINISHED |
| Object |
Adam Tan
Adam Tan is a Chinese business executive best known as a top leader of the HNA Group conglomerate.
|
E1069072
|
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: Adam Tan | Statement: [HNA Group, keyPerson, Adam Tan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Tan Context triple: [HNA Group, keyPerson, Adam Tan]
-
A.
Anthony Tan
Anthony Tan is a Malaysian entrepreneur best known as the co-founder and CEO of Grab, Southeast Asia’s leading super-app for ride-hailing, deliveries, and digital financial services.
-
B.
Vincent Tan
Vincent Tan is a Malaysian billionaire businessman and investor best known for owning multiple football clubs, including Cardiff City FC, and for founding the Berjaya Corporation conglomerate.
-
C.
Ken Seng
Ken Seng is a cinematographer known for his visually distinctive work on films such as "Obsessed."
-
D.
Andrew Tan
Andrew Tan is a Filipino billionaire businessman and real estate tycoon best known as the founder and chairman of Megaworld Corporation and a leading figure in the country’s property and liquor industries.
-
E.
Gabriel Goh
Gabriel Goh is a machine learning researcher known for his work at OpenAI, including co-developing the CLIP model for connecting images and text.
- 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: Adam Tan Triple: [HNA Group, keyPerson, Adam Tan]
Generated description
Adam Tan is a Chinese business executive best known as a top leader of the HNA Group conglomerate.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Adam Tan Target entity description: Adam Tan is a Chinese business executive best known as a top leader of the HNA Group conglomerate.
-
A.
Anthony Tan
Anthony Tan is a Malaysian entrepreneur best known as the co-founder and CEO of Grab, Southeast Asia’s leading super-app for ride-hailing, deliveries, and digital financial services.
-
B.
Vincent Tan
Vincent Tan is a Malaysian billionaire businessman and investor best known for owning multiple football clubs, including Cardiff City FC, and for founding the Berjaya Corporation conglomerate.
-
C.
Ken Seng
Ken Seng is a cinematographer known for his visually distinctive work on films such as "Obsessed."
-
D.
Andrew Tan
Andrew Tan is a Filipino billionaire businessman and real estate tycoon best known as the founder and chairman of Megaworld Corporation and a leading figure in the country’s property and liquor industries.
-
E.
Gabriel Goh
Gabriel Goh is a machine learning researcher known for his work at OpenAI, including co-developing the CLIP model for connecting images and text.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de27260ae08190be45b4b15898e365 |
completed | April 14, 2026, 11:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c72a345481908f8552bca7bb1a5a |
completed | May 3, 2026, 10:07 p.m. |
| NEDg | Description generation | batch_69f7c8d477f881908f8cfd2783e7f10f |
completed | May 3, 2026, 10:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7ca27ffd4819080bccd6bfd88ddb3 |
completed | May 3, 2026, 10:20 p.m. |
Created at: April 9, 2026, 10:16 p.m.