Triple
T901249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingsmill massacre |
E19450
|
entity |
| Predicate | victimReligion |
P6432
|
FINISHED |
| Object | Protestant |
—
|
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: Protestant | Statement: [Kingsmill massacre, victimReligion, Protestant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victimReligion Context triple: [Kingsmill massacre, victimReligion, Protestant]
-
A.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
B.
religiousTarget
chosen
Indicates that an action, policy, or behavior is directed at someone or something specifically because of their religion or religious affiliation.
-
C.
religiousElement
Indicates that something is a component, aspect, or feature associated with a religion or religious practice.
-
D.
ethnicReligion
Indicates that a religion is closely associated with a particular ethnic group, often tied to that group’s culture, ancestry, or identity.
-
E.
religiousConsequence
Indicates a relationship where one event, action, or state leads to an outcome specifically defined or understood in religious terms (such as divine reward, punishment, obligation, or spiritual effect).
- 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad4412408190a6bf8fc7484a5781 |
completed | March 1, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69a4aa979d408190b17ccfde132ea628 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.