Triple
T18777808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troy |
E459176
|
entity |
| Predicate | besiegedForDuration |
P53953
|
FINISHED |
| Object | ten years (mythological tradition) |
—
|
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: ten years (mythological tradition) | Statement: [Troy, besiegedForDuration, ten years (mythological tradition)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: besiegedForDuration Context triple: [Troy, besiegedForDuration, ten years (mythological tradition)]
-
A.
siegeDuration
chosen
Indicates the length of time that a siege persists from its beginning to its end.
-
B.
besiegedIn
Indicates that one entity is under siege at, or during the event of, another specified location or time.
-
C.
wasBesiegedBy
Indicates that an entity (typically a place or stronghold) was subjected to a military siege carried out by another entity.
-
D.
battleDuration
Indicates the length of time for which a particular battle or combat event lasts.
-
E.
sieged
Indicates that one entity has surrounded and blockaded another entity or location, typically to cut off supplies and force surrender.
- 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5933c640081909bb6fbaa1a21d411 |
completed | April 20, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69e48d1126e4819099607837ed5aadca |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:52 a.m.