Triple
T1706366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sierra Maestra campaign |
E36880
|
entity |
| Predicate | hasStartEvent |
P6285
|
FINISHED |
| Object | landing of the yacht Granma |
—
|
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: landing of the yacht Granma | Statement: [Sierra Maestra campaign, hasStartEvent, landing of the yacht Granma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStartEvent Context triple: [Sierra Maestra campaign, hasStartEvent, landing of the yacht Granma]
-
A.
hasTimeStart
Indicates that an event, process, or state begins at a specific point in time.
-
B.
hasBoundaryEvent
Indicates that an event occurs at or defines the boundary or limit of another entity or process.
-
C.
hasPrecedingEvents
Indicates that one or more events occurred earlier in time or sequence relative to the referenced event.
-
D.
hasInitial
Indicates that one entity possesses or is associated with the first letter or starting character of another entity’s name or value.
-
E.
hasSubEvent
chosen
Indicates that an event is composed of, or includes as part of its structure, another event that occurs within it.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab75ad24408190814069e6e3ef9e59 |
completed | March 7, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69aa61bad17c8190861b92cfb423f68f |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.