Triple
T2689399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Lawrence |
E57562
|
entity |
| Predicate | legendaryDeath |
P41523
|
FINISHED |
| Object | roasted alive on a gridiron |
—
|
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: roasted alive on a gridiron | Statement: [Saint Lawrence, legendaryDeath, roasted alive on a gridiron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legendaryDeath Context triple: [Saint Lawrence, legendaryDeath, roasted alive on a gridiron]
-
A.
deathDescribedIn
Indicates that a person's death is documented, narrated, or otherwise detailed within a particular source or description.
-
B.
deathBefore
Indicates that one entity’s death occurred earlier in time than another entity’s death.
-
C.
deifiedPersonDeathCause
Indicates the cause or manner of death of the person who is venerated or treated as a deity.
-
D.
deathDescribedAs
Indicates that one entity characterizes, portrays, or refers to another entity’s death using a particular description, metaphor, or wording.
-
E.
traditionallyDiedIn
Indicates that, according to tradition or customary accounts (rather than strictly verified historical evidence), one entity is said to have died in the location or context of another entity.
- F. None of above. chosen
Provenance (4 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_69ab4a5028388190a36f3baf1588309e |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd9f380d48190953529d23688a328 |
completed | March 7, 2026, 7:55 a.m. |
| PD | Predicate disambiguation | batch_69abd81c9b4c81908e5e0da6ac5f828b |
completed | March 7, 2026, 7:47 a.m. |
| PDg | Predicate description generation | batch_69abd891bcd481909af5340a64ff69f9 |
completed | March 7, 2026, 7:49 a.m. |
Created at: March 6, 2026, 9:54 p.m.