Triple
T18970279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union of Tanganyika and Zanzibar |
E464147
|
entity |
| Predicate | languageOfUnion |
P133990
|
FINISHED |
| Object | Swahili |
—
|
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: Swahili | Statement: [Union of Tanganyika and Zanzibar, languageOfUnion, Swahili]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageOfUnion Context triple: [Union of Tanganyika and Zanzibar, languageOfUnion, Swahili]
-
A.
majorityLanguageOf
Indicates that a given language is the primary or most widely spoken language within a specified group, region, or entity.
-
B.
languageOfFounders
Indicates the language or languages spoken or used by the founders of an entity.
-
C.
isWorkingLanguageOf
Indicates that a particular language is officially used as a medium of work, communication, or operation within a specified organization, institution, or context.
-
D.
nationalLanguageSpoken
Indicates that a particular language is officially recognized and commonly used as a national language within a given country or region.
-
E.
languageOfMembers
Indicates that the specified language is used or spoken by the members of a given group or organization.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d619acbc8190acb49b3fae707758 |
completed | April 20, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f437648190b85650dae8885d48 |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, noon