Triple
T16894183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jerzy Skolimowski |
E424254
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | EO |
E1239972
|
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: EO | Statement: [Jerzy Skolimowski, directed, EO]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EO Context triple: [Jerzy Skolimowski, directed, EO]
-
A.
EO
chosen
EO is a 2022 Polish drama film directed by Jerzy Skolimowski that follows the journey of a donkey across modern Europe, offering a poignant, minimalist reflection on humanity and animal suffering.
-
B.
EO
EO is the IATA airline designator assigned to Pegas Fly, a Russian passenger airline.
-
C.
ENO
ENO is a major London-based opera company known for performing operas in English and making the art form widely accessible.
-
D.
ERO
ERO is a division of U.S. Immigration and Customs Enforcement responsible for identifying, detaining, and removing individuals who violate immigration laws.
-
E.
ERO
ERO is the ICAO airline designator assigned to Sun d'Or International Airlines, an Israeli charter carrier affiliated with El Al.
- 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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3c8d6bfc88190b6b47b89c1135871 |
completed | April 18, 2026, 6:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfca11bc8190b0835de0d56ca0b1 |
completed | May 10, 2026, 6:34 p.m. |
Created at: April 10, 2026, 5:29 a.m.