Triple
T34752509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ticonderoga-class cruiser |
E1001819
|
entity |
| Predicate | laterUnitsFeature |
P201983
|
FINISHED |
| Object | Mk 41 Vertical Launching System |
—
|
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: Mk 41 Vertical Launching System | Statement: [Ticonderoga-class cruiser, laterUnitsFeature, Mk 41 Vertical Launching System]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterUnitsFeature Context triple: [Ticonderoga-class cruiser, laterUnitsFeature, Mk 41 Vertical Launching System]
-
A.
laterFeature
Indicates that one feature, event, or element occurs or is introduced after another in time.
-
B.
earlyUnitsFeature
Indicates that certain units or components are available or active earlier than usual within a sequence, process, or timeline.
-
C.
laterLeadsUnit
Indicates that an entity assumes leadership of a unit at a time later than another referenced point or leader.
-
D.
laterEntriesFeature
Indicates that the referenced entries appear at a later point in a sequence, timeline, or ordered collection than the current entry.
-
E.
hasUnitFeature
Indicates that something possesses a specific unit-related characteristic or attribute, such as a measurable feature expressed in defined units.
- F. None of above. chosen
Provenance (4 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_69f76db0fb30819096709d43f9a1f45f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a003ffb548081908ba64fd2b570f42f |
completed | May 10, 2026, 8:21 a.m. |
| PD | Predicate disambiguation | batch_6a003fcecf788190a13dff38b9de3414 |
completed | May 10, 2026, 8:20 a.m. |
| PDg | Predicate description generation | batch_6a003ffa64e48190b37cce7d1c939b78 |
completed | May 10, 2026, 8:21 a.m. |
Created at: May 3, 2026, 3:59 p.m.