Triple
T1841987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FAMAS assault rifle |
E41196
|
entity |
| Predicate | designer |
P184
|
FINISHED |
| Object |
Paul Tellie
Paul Tellie is a French firearms engineer best known for creating the FAMAS bullpup assault rifle used by the French military.
|
E207025
|
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: Paul Tellie | Statement: [FAMAS assault rifle, designer, Paul Tellie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Tellie Context triple: [FAMAS assault rifle, designer, Paul Tellie]
-
A.
Kasey the Kangaroo
Kasey the Kangaroo is the energetic kangaroo mascot representing the University of Missouri–Kansas City at athletic events and campus activities.
-
B.
Moe the Kangaroo
Moe the Kangaroo is the costumed kangaroo mascot that represents the Virginia Military Institute at its athletic events and school functions.
-
C.
Wool E. Bull
Wool E. Bull is the costumed bovine mascot of the Durham Bulls minor league baseball team, known for entertaining fans with on-field antics and community appearances.
-
D.
Alby
Alby is a residential suburban locality within Botkyrka Municipality in the Stockholm metropolitan area of Sweden.
-
E.
Spud Wilkinson
Spud Wilkinson is a person known primarily as a notable bearer of the surname Wilkinson.
- 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: Paul Tellie Triple: [FAMAS assault rifle, designer, Paul Tellie]
Generated description
Paul Tellie is a French firearms engineer best known for creating the FAMAS bullpup assault rifle used by the French military.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paul Tellie Target entity description: Paul Tellie is a French firearms engineer best known for creating the FAMAS bullpup assault rifle used by the French military.
-
A.
Kasey the Kangaroo
Kasey the Kangaroo is the energetic kangaroo mascot representing the University of Missouri–Kansas City at athletic events and campus activities.
-
B.
Moe the Kangaroo
Moe the Kangaroo is the costumed kangaroo mascot that represents the Virginia Military Institute at its athletic events and school functions.
-
C.
Wool E. Bull
Wool E. Bull is the costumed bovine mascot of the Durham Bulls minor league baseball team, known for entertaining fans with on-field antics and community appearances.
-
D.
Alby
Alby is a residential suburban locality within Botkyrka Municipality in the Stockholm metropolitan area of Sweden.
-
E.
Spud Wilkinson
Spud Wilkinson is a person known primarily as a notable bearer of the surname Wilkinson.
- 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_69a88648cd44819093303206d96d76ad |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb03e7a7481909c5b902034390ef1 |
completed | March 7, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adc9be1ef481909cd6f6975bf2165d |
completed | March 8, 2026, 7:10 p.m. |
| NEDg | Description generation | batch_69adcaf078a0819082c4bb48a3820ada |
completed | March 8, 2026, 7:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adce8a68848190ab56f5df7311dbca |
completed | March 8, 2026, 7:31 p.m. |
Created at: March 4, 2026, 7:33 p.m.