Triple
T32703431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloodhound missile (later marks) |
E836204
|
entity |
| Predicate | subsequentVersion |
P47516
|
FINISHED |
| Object | Bloodhound Mk II |
—
|
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: Bloodhound Mk II | Statement: [Bloodhound missile (later marks), subsequentVersion, Bloodhound Mk II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subsequentVersion Context triple: [Bloodhound missile (later marks), subsequentVersion, Bloodhound Mk II]
-
A.
hasSubsequentVersion
Indicates that one entity is a later or updated version that follows another entity in a version sequence.
-
B.
laterVersion
chosen
Indicates that one entity is a subsequent or more recent version of another entity in a version sequence.
-
C.
subsequentReleaseFormat
Indicates that one media release is issued in a different format that chronologically follows an earlier release of the same content.
-
D.
subsequentView
Indicates that one viewing event occurs after another in temporal order.
-
E.
subsequentIncrease
Indicates that one quantity or value increases after a prior event, state, or change has occurred.
- 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_69f3493323288190a4e88251035fe96e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:10 a.m.