Triple
T19670609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Amsterdam |
E472324
|
entity |
| Predicate | hasThemeInLiterature |
P61759
|
FINISHED |
| Object | defence of a city |
—
|
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: defence of a city | Statement: [siege of Amsterdam, hasThemeInLiterature, defence of a city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasThemeInLiterature Context triple: [siege of Amsterdam, hasThemeInLiterature, defence of a city]
-
A.
literaryThemeInvolvement
chosen
Indicates the involvement or presence of a particular literary theme within a work, passage, or character arc.
-
B.
hasLiterarySignificance
Indicates that something holds notable importance, influence, or value within the realm of literature or literary studies.
-
C.
hasReputationInLiterature
Indicates that an entity is recognized or regarded in a particular way within literary works or the field of literature.
-
D.
functionInLiterature
Indicates that one entity serves a particular narrative, rhetorical, or thematic role within a literary work in relation to another entity.
-
E.
hasViewOnLiterature
Indicates that an entity holds a particular opinion, perspective, or stance regarding literature.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416b9cf8819096f44e3f9fbf86fa |
completed | April 20, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69e514eb37b8819091502cc954f70eba |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.