Triple
T27292072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amha Selassie I |
E688654
|
entity |
| Predicate | afterEventRole |
P138651
|
FINISHED |
| Object | Emperor of Ethiopia in exile |
—
|
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: Emperor of Ethiopia in exile | Statement: [Amha Selassie I, afterEventRole, Emperor of Ethiopia in exile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterEventRole Context triple: [Amha Selassie I, afterEventRole, Emperor of Ethiopia in exile]
-
A.
usedAfterEventFor
Indicates that one entity is used only after a specified event has occurred or been completed.
-
B.
subsequentRole
chosen
Indicates that one role or position is held after, and in succession to, another role or position.
-
C.
settingAfterEvent
Indicates that a particular setting or state occurs subsequent to, and as a result of or in temporal sequence with, a specified event.
-
D.
capitalAfterEvent
Indicates that a location became the capital of a political or administrative entity as a result of, or following, a specific event.
-
E.
createdAfterEvent
Indicates that the creation of one entity occurred after a specified event in time.
- 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_69ef355a96308190a2bed991525fb278 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c1f94ac8190bc6fbc7916fc0d82 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 11:16 a.m.