Triple
T13011087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Winners |
E322409
|
entity |
| Predicate | hasFanIdentity |
P69827
|
FINISHED |
| Object | working-class roots of Marseille |
—
|
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: working-class roots of Marseille | Statement: [South Winners, hasFanIdentity, working-class roots of Marseille]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFanIdentity Context triple: [South Winners, hasFanIdentity, working-class roots of Marseille]
-
A.
hasFan
Indicates that an entity is the admirer, supporter, or enthusiast of another entity.
-
B.
hasIdentity
Indicates that one entity is the same as, or is identified as, another specific entity or identifier.
-
C.
hasFanActivity
Indicates that an entity is associated with actions, behaviors, or engagement carried out by fans in relation to it.
-
D.
hasFanBaseFrom
chosen
Indicates that an entity has a significant group of supporters or followers originating from a specified place, group, or source.
-
E.
hasFanPerception
Indicates that an entity is perceived, interpreted, or regarded in a particular way by its fans or fan community.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e9e14b88190a2cee8e0c9bf31c8 |
completed | April 10, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69d97dc153a081909d13a694993f074a |
completed | April 10, 2026, 10:46 p.m. |
Created at: April 9, 2026, 8:49 p.m.