Triple
T6235986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Gravelines (1588) |
E139478
|
entity |
| Predicate | EnglishLosses |
P8356
|
FINISHED |
| Object | light in ships |
—
|
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: light in ships | Statement: [Battle of Gravelines (1588), EnglishLosses, light in ships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: EnglishLosses Context triple: [Battle of Gravelines (1588), EnglishLosses, light in ships]
-
A.
englishFlagship
Indicates that an entity participates in or is associated with an English flagship program (typically an intensive, advanced English language or studies track).
-
B.
losses
chosen
Indicates that an entity experiences a decrease in value, quantity, or advantage as a result of some event or comparison.
-
C.
EnglishCommander
Indicates that one entity serves as a military commander or leader for English forces in relation to another entity.
-
D.
EnglishTranslation
Indicates that one expression is the English-language translation equivalent of another expression.
-
E.
fleetStrengthEnglish
Indicates the relative military or naval power level associated with a fleet, expressed or categorized in English terms.
- 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062f236608190997e77b41095883f |
completed | March 22, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69c05601de6481909d0880048fd7b49a |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:23 p.m.