Triple
T4316231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Szilard petition |
E96397
|
entity |
| Predicate | expressesConcernAbout |
P17598
|
FINISHED |
| Object | killing of civilians |
—
|
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: killing of civilians | Statement: [Szilard petition, expressesConcernAbout, killing of civilians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expressesConcernAbout Context triple: [Szilard petition, expressesConcernAbout, killing of civilians]
-
A.
concern
Indicates that one entity is about, relates to, or is of interest or importance to another entity.
-
B.
raisedConcernAbout
chosen
Indicates that one entity has expressed worry, doubt, or objection regarding another entity or issue.
-
C.
concernedEvent
Indicates that an entity has a concern, involvement, or relevance specifically with respect to a particular event.
-
D.
concernsRight
Indicates that something is about or relates specifically to a legal or moral right held by an entity.
-
E.
concernedProperty
Indicates that one entity is about, involves, or pertains to a particular property or attribute of another entity.
- 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_69b345422aac81909ddbadae437d122e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350f60dfc819098202b7eb3bbf402 |
completed | March 12, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69b34f4a07b08190a06ada0d9cbb14fb |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:12 p.m.