Triple
T9442606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heraclea |
E227683
|
entity |
| Predicate | partOfLeague |
P21421
|
FINISHED |
| Object | Italian Greek cities |
—
|
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: Italian Greek cities | Statement: [Heraclea, partOfLeague, Italian Greek cities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfLeague Context triple: [Heraclea, partOfLeague, Italian Greek cities]
-
A.
isPartOfLeague
chosen
Indicates that an entity belongs to, participates in, or is a member of a particular league.
-
B.
basedInLeague
Indicates that an entity (such as a team or club) participates in, belongs to, or is officially associated with a particular league.
-
C.
league
Indicates that an organization or team participates in, is a member of, or is associated with a particular sports or competitive league.
-
D.
affiliateLeague
Indicates that one sports organization or team is formally associated with and operates under the umbrella or partnership of a particular league.
-
E.
countryLeagueRepresents
Indicates that a particular league serves as the official representative or embodiment of a country in a given sport or competitive context.
- 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_69ca843884488190ad6cbe0153088234 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f300cc88190a793712706295c53 |
completed | April 1, 2026, 8:25 p.m. |
| PD | Predicate disambiguation | batch_69cca5596ffc819097e9c8eefd4ef9b8 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:50 p.m.