Triple
T26522061
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Histoire des Girondins |
E669981
|
entity |
| Predicate | portraysAsHeroes |
P100368
|
FINISHED |
| Object | Girondin deputies |
—
|
NE NERFINISHED |
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: Girondin deputies | Statement: [Histoire des Girondins, portraysAsHeroes, Girondin deputies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysAsHeroes Context triple: [Histoire des Girondins, portraysAsHeroes, Girondin deputies]
-
A.
heroDepicted
Indicates that one entity is portrayed or represented as a hero in relation to another entity.
-
B.
includesHeroes
Indicates that something (such as a work, group, or collection) contains or features one or more heroes as part of it.
-
C.
hasHumanProtagonists
Indicates that the primary characters driving the narrative are human beings rather than non-human entities.
-
D.
portraysPersonAs
chosen
Indicates that one entity represents, depicts, or characterizes another person in a particular way or role.
-
E.
heroPerformsFor
Indicates that a hero carries out an action or performance for the benefit, entertainment, or service 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_69eeb31b6dcc8190b30632dc3928a0c0 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 27, 2026, 1:28 a.m.