Triple
T25978965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masulipatam |
E646017
|
entity |
| Predicate | hadTradingLinksWith |
P75307
|
FINISHED |
| Object | Southeast Asia |
—
|
NE NERFINISHED |
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: Southeast Asia | Statement: [Masulipatam, hadTradingLinksWith, Southeast Asia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadTradingLinksWith Context triple: [Masulipatam, hadTradingLinksWith, Southeast Asia]
-
A.
hasTrade
Indicates a relationship where one entity engages in or maintains a commercial exchange or trading activity with another entity.
-
B.
hasHistoricalOrAffiliateLinkTo
Indicates that one entity is historically connected to, or has an affiliate/partnership relationship with, another entity.
-
C.
hadURL
Indicates that an entity was associated with or linked to a specific URL at some point in time.
-
D.
tradedTo
Indicates that ownership or contractual rights to an entity (such as a player, asset, or item) were transferred from one party to another, typically as part of an exchange or deal.
-
E.
hadTradingPostNetwork
chosen
Indicates that an entity maintained or controlled a network of trading posts used for commercial exchange or trade activities.
- F. None of above.
Provenance (3 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6050d0a808190837a1fd676f604f4 |
completed | May 2, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 8:53 a.m.