Triple
T16525139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Running Blind |
E401414
|
entity |
| Predicate | featuresVictims |
P36783
|
FINISHED |
| Object | former female U.S. Army soldiers |
—
|
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: former female U.S. Army soldiers | Statement: [Running Blind, featuresVictims, former female U.S. Army soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresVictims Context triple: [Running Blind, featuresVictims, former female U.S. Army soldiers]
-
A.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
B.
coVictim
Indicates that two or more entities are victims in the same harmful event or incident.
-
C.
mainVictims
chosen
Indicates that the related entities are the primary or principal targets harmed or affected by an action, event, or perpetrator.
-
D.
hasVictims
Indicates that an entity has one or more individuals who have been harmed, injured, or adversely affected by it.
-
E.
victimGroupHelped
Indicates that assistance, support, or aid was provided to a group identified as victims.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed323c081908218460aa4ae3cf6 |
completed | April 18, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69e296995d388190b88ebe189dce890d |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.