Triple
T31766980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akokoro |
E810835
|
entity |
| Predicate | locatedInFormerHomelandOf |
P149258
|
FINISHED |
| Object | Milton Obote |
E231969
|
NE 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: Milton Obote | Statement: [Akokoro, locatedInFormerHomelandOf, Milton Obote]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInFormerHomelandOf Context triple: [Akokoro, locatedInFormerHomelandOf, Milton Obote]
-
A.
locatedInFormerColonyOf
Indicates that one entity is geographically situated within a territory that was formerly a colony of another entity.
-
B.
usedToBeHomelandOf
Indicates that a place previously served as the homeland or native territory of a particular group or entity, but no longer does so.
-
C.
isInFormerHomeland
chosen
Indicates that an entity is located within a territory that was once its homeland but is no longer officially recognized as such.
-
D.
partOfAncestralHomelandOf
Indicates that one entity constitutes a geographic or cultural portion of the ancestral homeland associated with another entity.
-
E.
isLocatedInPresentDayCountry
Indicates that an entity’s location is specified in terms of the modern, currently recognized country that encompasses it.
- F. None of above.
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_69f348e463e08190b902d4819195e1f0 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a01bdacb52481909c56b0398106640e |
completed | May 11, 2026, 11:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2f0bb0ec84819092ed7394a409a579 |
completed | June 14, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_6a01bd30c8ec8190b1e54d7658b01a8d |
completed | May 11, 2026, 11:27 a.m. |
Created at: April 30, 2026, 11:32 p.m.