Triple
T36731983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Achilles' armor |
E907364
|
entity |
| Predicate | strippedFrom |
P16758
|
FINISHED |
| Object | corpse of Patroclus |
—
|
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: corpse of Patroclus | Statement: [Achilles' armor, strippedFrom, corpse of Patroclus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strippedFrom Context triple: [Achilles' armor, strippedFrom, corpse of Patroclus]
-
A.
removedFrom
chosen
Indicates that one entity has been taken away, extracted, or detached from another entity or context.
-
B.
cutFrom
Indicates that one entity has been removed or separated from another entity by cutting.
-
C.
removedUnder
Indicates that one entity was taken away, eliminated, or withdrawn while being subject to the authority, control, or conditions imposed by another entity.
-
D.
removedAs
Indicates that one entity has been taken out of a position, role, or context in relation to another entity.
-
E.
removedAfter
Indicates that one entity is removed or deleted at a point in time that occurs after the removal or deletion of 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_69f76e75aa6881909b844d00a3888ee5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.