Triple
T8109482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astra Ploiești |
E189310
|
entity |
| Predicate | league |
P888
|
FINISHED |
| Object | Liga I |
E603161
|
NE 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: Liga I | Statement: [Astra Ploiești, league, Liga I]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liga I Context triple: [Astra Ploiești, league, Liga I]
-
A.
Liga I
chosen
Liga I is the top professional football division in Romania, featuring the country’s leading clubs in its premier league competition.
-
B.
Liga II
Liga II is the second tier of the Romanian professional football league system, sitting directly below Liga I.
-
C.
Liga 1
Liga 1 is the top-tier professional football league in Indonesia, featuring the country’s leading clubs in its premier competition.
-
D.
Ekstraklasa
Ekstraklasa is the top professional football league in Poland, featuring the country’s highest-level clubs.
-
E.
Liga Nacional
Liga Nacional is the top professional football league in Guatemala, featuring the country’s premier clubs in its highest competitive division.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82b9d5848190a24672775d5c5011 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb42fbc57c81908c6be87bbc547085 |
completed | March 31, 2026, 3:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbe994fc881908a43cfdf9f28753c |
completed | April 1, 2026, 6:43 a.m. |
Created at: March 30, 2026, 5:32 p.m.