Triple
T23374478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drac language |
E593567
|
entity |
| Predicate | hasWritingSystem |
P454
|
FINISHED |
| Object |
Drac script
Drac script is the writing system used to represent the Drac language in written form.
|
E593567
|
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: Drac script | Statement: [Drac language, hasWritingSystem, Drac script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drac script Context triple: [Drac language, hasWritingSystem, Drac script]
-
A.
Drac language
The Drac language is a fictional alien tongue spoken by the reptilian Drac species in the science fiction film "Enemy Mine."
-
B.
LScript
LScript is a scripting language used to automate tasks and extend functionality within the LightWave 3D computer graphics and animation software.
-
C.
BrainScript
BrainScript is a domain-specific scripting language developed for defining and training neural networks within the Microsoft Cognitive Toolkit (CNTK).
-
D.
Muhaqqaq script
Muhaqqaq script is a majestic, elongated style of Islamic calligraphy historically favored for large Qur’anic manuscripts and monumental inscriptions.
-
E.
Vai script
The Vai script is an indigenous syllabic writing system from Liberia and Sierra Leone, created in the 19th century by the Vai people to represent their own language.
- 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: Drac script Triple: [Drac language, hasWritingSystem, Drac script]
Generated description
Drac script is the writing system used to represent the Drac language in written form.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Drac script Target entity description: Drac script is the writing system used to represent the Drac language in written form.
-
A.
Drac language
chosen
The Drac language is a fictional alien tongue spoken by the reptilian Drac species in the science fiction film "Enemy Mine."
-
B.
LScript
LScript is a scripting language used to automate tasks and extend functionality within the LightWave 3D computer graphics and animation software.
-
C.
BrainScript
BrainScript is a domain-specific scripting language developed for defining and training neural networks within the Microsoft Cognitive Toolkit (CNTK).
-
D.
Muhaqqaq script
Muhaqqaq script is a majestic, elongated style of Islamic calligraphy historically favored for large Qur’anic manuscripts and monumental inscriptions.
-
E.
Vai script
The Vai script is an indigenous syllabic writing system from Liberia and Sierra Leone, created in the 19th century by the Vai people to represent their own language.
- F. None of above.
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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b1d24881909945936cbf00876e |
completed | April 29, 2026, 6:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5ddfbbf0819098166b60f5e5e62e |
completed | May 19, 2026, 12:55 p.m. |
| NEDg | Description generation | batch_6a0c5fc2cd908190b86c0f915db3a1e3 |
completed | May 19, 2026, 1:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c603b3ad08190b9bfead27448fc58 |
completed | May 19, 2026, 1:06 p.m. |
Created at: April 17, 2026, 5:33 p.m.