Triple
T27429117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Jean Collins |
E690576
|
entity |
| Predicate | relativeKilledIn |
P199974
|
FINISHED |
| Object | 16th Street Baptist Church bombing |
—
|
NE NERFINISHED |
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: 16th Street Baptist Church bombing | Statement: [Sarah Jean Collins, relativeKilledIn, 16th Street Baptist Church bombing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeKilledIn Context triple: [Sarah Jean Collins, relativeKilledIn, 16th Street Baptist Church bombing]
-
A.
killedBy
Indicates that one entity caused the death of another entity.
-
B.
killedNear
Indicates that one entity killed another in close spatial proximity to a specified location or reference point.
-
C.
killedOnBehalfOf
Indicates that one entity carried out a killing as a representative of, or in service to, another entity.
-
D.
killsOrIsKilledBy
Indicates that one entity causes the death of the other or is itself killed by that entity, capturing a mutual or directional lethal relationship between them.
-
E.
killedAlongWith
Indicates that one entity was killed at the same time and in the same event or circumstance as another entity.
- F. None of above. chosen
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_69ef52003fb48190b0f1295246182a86 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69ff691f5ae481908597ce245188d31c |
completed | May 9, 2026, 5:04 p.m. |
| PD | Predicate disambiguation | batch_69ff67ceeeb081909fd00cad166c4b6a |
completed | May 9, 2026, 4:58 p.m. |
| PDg | Predicate description generation | batch_69ff691e86d0819099fdb5eca5a95632 |
completed | May 9, 2026, 5:04 p.m. |
Created at: April 27, 2026, 12:41 p.m.