Triple
T11471422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black family |
E271916
|
entity |
| Predicate | statusDuringSecondWizardingWar |
P19322
|
FINISHED |
| Object | divided loyalties |
—
|
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: divided loyalties | Statement: [Black family, statusDuringSecondWizardingWar, divided loyalties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusDuringSecondWizardingWar Context triple: [Black family, statusDuringSecondWizardingWar, divided loyalties]
-
A.
statusDuringWar
chosen
Indicates the role, condition, or classification an entity held specifically during a period of war.
-
B.
statusDuringWorldWarII
Indicates the role, condition, or classification an entity had specifically during the period of World War II.
-
C.
stateDuringWar
Indicates that a state or condition exists specifically in the context of, or for the duration of, a war or armed conflict.
-
D.
operationInSecondBattle
Indicates that an entity participated in or was involved in a military operation that took place during the second battle of a given conflict.
-
E.
supportedDuringWar
Indicates that one entity provided assistance, resources, or backing to another entity specifically during a time of war.
- 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_69d6aae0c8d881908a5a360c0be3242e |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d82949e3688190b024a4980666c94f |
completed | April 9, 2026, 10:33 p.m. |
| PD | Predicate disambiguation | batch_69d8086ecd6c81908f424864857762d6 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:35 p.m.