Triple
T1482176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grab |
E30981
|
entity |
| Predicate | Tan Hooi LingRole |
P29262
|
FINISHED |
| Object | co-founder |
—
|
LITERAL FINISHED |
How this triple was built (2 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: co-founder | Statement: [Grab, Tan Hooi LingRole, co-founder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Tan Hooi LingRole Context triple: [Grab, Tan Hooi LingRole, co-founder]
-
A.
typeOfRole
Indicates that one entity specifies the kind or category of role that another entity holds or performs.
-
B.
namedPersonRole
Indicates that a person is identified by name as holding a specific role or position in a given context.
-
C.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
-
D.
roleInTaiwan
Indicates that an entity holds or has held an official or notable role, position, or function within the political, administrative, or social context of Taiwan.
-
E.
petitionerRole
Indicates the role or capacity in which a petitioner is acting within a legal or formal proceeding.
- F. None of above. chosen
Provenance (4 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_69a498fe55a88190ab7f9e40ace88e49 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c6782f088190930d25a56161e2b3 |
completed | March 1, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69a4c484e52c81908948ff8c0a42751b |
completed | March 1, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69a4c57984088190b2c2d2d9cc2e5df9 |
completed | March 1, 2026, 11:02 p.m. |
Created at: March 1, 2026, 8:11 p.m.