Triple
T21015016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magdalena Abakanowicz |
E517649
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Agora |
—
|
NE NERFINISHED |
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: Agora | Statement: [Magdalena Abakanowicz, notableWork, Agora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agora Context triple: [Magdalena Abakanowicz, notableWork, Agora]
-
A.
Agora
Agora is the industry-focused market and networking hub of the Thessaloniki International Film Festival, dedicated to supporting film professionals and promoting new projects.
-
B.
Agora
chosen
Agora is a 2009 historical drama film set in Roman Egypt that explores religious conflict and the life of philosopher Hypatia.
-
C.
Agoro
Agoro is a character featured as a component of the work "Necessary Evil."
-
D.
Agora Industry
Agora Industry is the Thessaloniki International Film Festival’s professional industry platform, dedicated to supporting film development, production, and networking among filmmakers and audiovisual professionals.
-
E.
Agori
Agori are a fictional race of small, villager-like characters from the Lego Bionicle universe, known for inhabiting the planet Bara Magna and supporting the Glatorian warriors.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5764188190829de6f5abd6e00f |
completed | April 21, 2026, 4:25 a.m. |
Created at: April 16, 2026, 1:54 p.m.