Triple
T3654247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trident II D5 |
E77491
|
entity |
| Predicate | treatyRelevance |
P5763
|
FINISHED |
| Object | subject to New START counting rules |
—
|
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: subject to New START counting rules | Statement: [Trident II D5, treatyRelevance, subject to New START counting rules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatyRelevance Context triple: [Trident II D5, treatyRelevance, subject to New START counting rules]
-
A.
relatedToTreaty
chosen
Indicates that there exists a connection, association, or relevance between an entity and a specific treaty or treaties.
-
B.
treatyFocus
Indicates that a treaty is primarily concerned with, directed toward, or centered on a particular subject, issue, or area.
-
C.
relevantSectionForTreaty
Indicates that a specific legal or textual section is pertinent or applicable to a given treaty.
-
D.
linkedToTreaty
Indicates that an entity has a formal connection or association with a specific treaty, such as being established by, governed by, or otherwise related to that treaty.
-
E.
treatyScope
Indicates the range, subject matter, or extent of issues and obligations that a treaty covers or applies to.
- 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_69ad85def5cc8190863dccf55a18bebb |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3b9164c81908938a4338430d193 |
completed | March 8, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69adb84650148190bf79231105e58d7f |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.