Triple
T25475107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grail |
E638409
|
entity |
| Predicate | hasSuccessorSystem |
P50932
|
FINISHED |
| Object | 9K34 Strela-3 |
—
|
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: 9K34 Strela-3 | Statement: [Grail, hasSuccessorSystem, 9K34 Strela-3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSuccessorSystem Context triple: [Grail, hasSuccessorSystem, 9K34 Strela-3]
-
A.
hasSuccessorScheme
Indicates that one scheme is the direct successor or follow-up to another scheme in a sequence or versioning relationship.
-
B.
hasOnlineSuccessor
Indicates that one entity is the direct online or digital successor of another, typically replacing or continuing its function in an online context.
-
C.
hasModernSuccessor
Indicates that an entity is followed or replaced by another entity that serves as its modern equivalent or continuation.
-
D.
successorSystem
chosen
Indicates that one system directly follows and replaces another in function, role, or version.
-
E.
hasSuccessorUsers
Indicates that one user or set of users is followed or replaced by another user or set of users in a sequence or succession.
- 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_69e75db9b964819096802dcf502e577e |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 21, 2026, 2:25 p.m.