Triple
T16458914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | siege of Athens |
E399753
|
entity |
| Predicate | demandByVictors |
P6231
|
FINISHED |
| Object | tearing down of the Long Walls |
—
|
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: tearing down of the Long Walls | Statement: [siege of Athens, demandByVictors, tearing down of the Long Walls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demandByVictors Context triple: [siege of Athens, demandByVictors, tearing down of the Long Walls]
-
A.
demand
chosen
Indicates that one entity requests or insists that another entity provide something or perform an action, often with an expectation of compliance.
-
B.
questedBy
Indicates that a quest or mission is initiated, assigned, or undertaken by a particular entity.
-
C.
wantedBy
Indicates that one entity is desired, sought, or wished for by another entity.
-
D.
winnerRepresents
Indicates that the winner of a competition or contest serves as a representative for a particular group, organization, or entity.
-
E.
promptedDemandFor
Indicates that one entity’s action or occurrence caused an increase in demand for another entity.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32d7ff0e881909100bb5b33c04291 |
completed | April 18, 2026, 7:06 a.m. |
| PD | Predicate disambiguation | batch_69e227048d608190a4205eae3117629a |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:10 a.m.