Triple
T18970303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union of Tanganyika and Zanzibar |
E464147
|
entity |
| Predicate | modernNameOfMainland |
P74746
|
FINISHED |
| Object | mainland Tanzania |
—
|
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: mainland Tanzania | Statement: [Union of Tanganyika and Zanzibar, modernNameOfMainland, mainland Tanzania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modernNameOfMainland Context triple: [Union of Tanganyika and Zanzibar, modernNameOfMainland, mainland Tanzania]
-
A.
modernNameOfArea
chosen
Indicates that one area entity represents the current or modern name of another area entity.
-
B.
modernNameOfficial
Indicates that an entity’s current, formally recognized name is the one specified.
-
C.
modernNameOfServedSettlement
Indicates that the object is the current, modern name of the settlement that is or was served by the subject (e.g., a facility, infrastructure, or service).
-
D.
modernNameForm
Indicates that one entity is the contemporary or currently used name form corresponding to another entity’s name.
-
E.
capitalFoundedModernName
Indicates that the capital city was founded under a different historical name than the one it is known by in modern times.
- 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_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. |
Created at: April 10, 2026, noon