Triple
T7346789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gojek |
E169399
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object |
GoSend
GoSend is Gojek’s on-demand courier and delivery service that enables users to send packages quickly within a city.
|
E659408
|
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: GoSend | Statement: [Gojek, hasService, GoSend]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GoSend Context triple: [Gojek, hasService, GoSend]
-
A.
Sendim
Sendim is a town in northeastern Portugal known for its Mirandese-speaking community and distinct local culture.
-
B.
Talk 'N Text Tropang Texters
Talk 'N Text Tropang Texters is a professional basketball team in the Philippine Basketball Association (PBA), known for its multiple championships and corporate backing by the PLDT group.
-
C.
WeTransfer
WeTransfer is a cloud-based file transfer service that enables users to easily send large files over the internet.
-
D.
Media Mail
Media Mail is a discounted U.S. Postal Service shipping option specifically for sending educational materials and media such as books, sound recordings, and DVDs.
-
E.
MSGS
MSGS is the stock ticker symbol for Madison Square Garden Sports Corp., a publicly traded company that owns and operates professional sports franchises and related entertainment assets.
- 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: GoSend Triple: [Gojek, hasService, GoSend]
Generated description
GoSend is Gojek’s on-demand courier and delivery service that enables users to send packages quickly within a city.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: GoSend Target entity description: GoSend is Gojek’s on-demand courier and delivery service that enables users to send packages quickly within a city.
-
A.
Sendim
Sendim is a town in northeastern Portugal known for its Mirandese-speaking community and distinct local culture.
-
B.
Talk 'N Text Tropang Texters
Talk 'N Text Tropang Texters is a professional basketball team in the Philippine Basketball Association (PBA), known for its multiple championships and corporate backing by the PLDT group.
-
C.
WeTransfer
WeTransfer is a cloud-based file transfer service that enables users to easily send large files over the internet.
-
D.
Media Mail
Media Mail is a discounted U.S. Postal Service shipping option specifically for sending educational materials and media such as books, sound recordings, and DVDs.
-
E.
MSGS
MSGS is the stock ticker symbol for Madison Square Garden Sports Corp., a publicly traded company that owns and operates professional sports franchises and related entertainment assets.
- 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_69c68a5878888190968ce4d04db8d69f |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0f0329c8190a0182e3bf62604e5 |
completed | March 27, 2026, 9:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7fa916ac881909acee8184b71dc85 |
completed | March 28, 2026, 3:58 p.m. |
| NEDg | Description generation | batch_69c7fb05966c819089f47be0b9d32cb2 |
completed | March 28, 2026, 4 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7fddb63908190a5123ed8d7c9be1f |
completed | March 28, 2026, 4:12 p.m. |
Created at: March 27, 2026, 3:05 p.m.