Triple
T13856163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chevaleret |
E333068
|
entity |
| Predicate | followedOnLine6By |
P50088
|
FINISHED |
| Object | Nationale |
—
|
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: Nationale | Statement: [Chevaleret, followedOnLine6By, Nationale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followedOnLine6By Context triple: [Chevaleret, followedOnLine6By, Nationale]
-
A.
followedIn
Indicates that one entity began following or subscribing to another entity, typically in a social or sequential context.
-
B.
followsBy
chosen
Indicates that one event, state, or entity occurs or comes immediately after another in a sequence or order.
-
C.
eraFollowed
Indicates that one historical era comes directly after another in chronological sequence.
-
D.
followerOf
Indicates that one entity subscribes to, tracks, or regularly receives updates from another entity, typically in a social or informational context.
-
E.
followedSign
Indicates that an entity proceeded in accordance with, or took action based on, a particular sign or posted instruction.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02dc9f488190b7181dcb7e304632 |
completed | April 14, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:14 p.m.