Triple
T2747914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AJ Auxerre |
E60913
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
AJA
AJA is a French professional football club based in Auxerre, known for its strong youth academy and history in Ligue 1 and European competitions.
|
E296159
|
NE FINISHED |
How this triple was built (4 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: AJA | Statement: [AJ Auxerre, nickname, AJA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AJA Context triple: [AJ Auxerre, nickname, AJA]
-
A.
AJ
AJ is a leading peer-reviewed scientific journal in astronomy and astrophysics, publishing research on the structure and evolution of the universe.
-
B.
AJS
AJS is the standard abbreviation for the American Journal of Science, a long-running, peer-reviewed scientific journal primarily focused on geology and related earth sciences.
-
C.
A’ja
A’ja is the given name of A’ja Wilson, a prominent American professional basketball player and WNBA star.
-
D.
JASA
JASA is a leading peer-reviewed scientific journal that publishes research on the science and applications of acoustics.
-
E.
ajika
Ajika is a spicy Georgian-Abkhazian chili paste or sauce, typically made with hot peppers, garlic, herbs, and spices, and widely used to season meats and other dishes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: AJA Triple: [AJ Auxerre, nickname, AJA]
Generated description
AJA is a French professional football club based in Auxerre, known for its strong youth academy and history in Ligue 1 and European competitions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AJA Target entity description: AJA is a French professional football club based in Auxerre, known for its strong youth academy and history in Ligue 1 and European competitions.
-
A.
AJ
AJ is a leading peer-reviewed scientific journal in astronomy and astrophysics, publishing research on the structure and evolution of the universe.
-
B.
AJS
AJS is the standard abbreviation for the American Journal of Science, a long-running, peer-reviewed scientific journal primarily focused on geology and related earth sciences.
-
C.
A’ja
A’ja is the given name of A’ja Wilson, a prominent American professional basketball player and WNBA star.
-
D.
JASA
JASA is a leading peer-reviewed scientific journal that publishes research on the science and applications of acoustics.
-
E.
ajika
Ajika is a spicy Georgian-Abkhazian chili paste or sauce, typically made with hot peppers, garlic, herbs, and spices, and widely used to season meats and other dishes.
- F. None of above. chosen
Provenance (5 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_69ab4b79846081909096725374d65ce9 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb4ff7b08190b72edb6a2bc5fd19 |
completed | March 7, 2026, 8:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afbbd341a88190ae0f5eb94a6fdc92 |
completed | March 10, 2026, 6:36 a.m. |
| NEDg | Description generation | batch_69afbd8563248190af593099ecae84ee |
completed | March 10, 2026, 6:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69afbdb28a708190bbd4bc6632b8e137 |
completed | March 10, 2026, 6:44 a.m. |
Created at: March 6, 2026, 9:56 p.m.