Triple
T23871274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bagne of Toulon |
E592735
|
entity |
| Predicate | workPerformed |
P37598
|
FINISHED |
| Object | arsenal work |
—
|
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: arsenal work | Statement: [Bagne of Toulon, workPerformed, arsenal work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workPerformed Context triple: [Bagne of Toulon, workPerformed, arsenal work]
-
A.
performsWorkOf
Indicates that one entity carries out, executes, or fulfills the tasks, functions, or role that are normally associated with another entity.
-
B.
performsWork
chosen
Indicates that one entity carries out, executes, or engages in work or tasks for or on behalf of another entity or context.
-
C.
performedInWorkBy
Indicates that an action or role was carried out within a specific work (e.g., a film, book, or composition) by a particular agent or contributor.
-
D.
workOn
Indicates that an agent is actively engaged in performing tasks or making progress on a particular project, object, or assignment.
-
E.
performedWorkBy
Indicates that a particular work, task, or activity was carried out or executed by a specified agent or 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_69e25d23a5c88190ae3999c70ca15e08 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cbfe1f948190ad2c0d5bbe0c7240 |
completed | April 29, 2026, 9:14 a.m. |
| PD | Predicate disambiguation | batch_69f1614a65a88190bde1efb368a151e4 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:14 p.m.