Triple
T35920040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Maqamat of al-Hariri |
E1038854
|
entity |
| Predicate | firstLatinTranslator |
P95879
|
FINISHED |
| Object |
Thomas Erpenius
Thomas Erpenius was a prominent early 17th-century Dutch Orientalist and Arabist known for his pioneering work in Arabic studies and influential grammars and translations in Europe.
|
E2162029
|
NE FINISHED |
How this triple was built (3 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: Thomas Erpenius | Statement: [The Maqamat of al-Hariri, firstLatinTranslator, Thomas Erpenius]
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: Thomas Erpenius Triple: [The Maqamat of al-Hariri, firstLatinTranslator, Thomas Erpenius]
Generated description
Thomas Erpenius was a prominent early 17th-century Dutch Orientalist and Arabist known for his pioneering work in Arabic studies and influential grammars and translations in Europe.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLatinTranslator Context triple: [The Maqamat of al-Hariri, firstLatinTranslator, Thomas Erpenius]
-
A.
latinTranslator
Indicates that one entity translates text or speech into Latin for another entity or context.
-
B.
wasFirstLatinTranslationBy
chosen
Indicates that one entity is the earliest Latin translation of another entity, produced by a specified translator or source.
-
C.
firstLatinTranslationDate
Indicates the date on which something was first translated into Latin.
-
D.
firstEnglishTranslators
Indicates that the subject is among the earliest individuals or groups to translate the object into English.
-
E.
formerTransliteration
Indicates that one transliteration was previously used for an entity but has since been replaced by a different transliteration.
- F. None of above.
Provenance (6 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_69f76e2320748190b7f5c4750d0cd0d3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037ce70f54819082946dad8d380825 |
completed | May 12, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38ae3392108190b77662fafc54e35a |
completed | June 22, 2026, 3:38 a.m. |
| NEDg | Description generation | batch_6a38aeef45b88190bd73e62d7b0ad345 |
completed | June 22, 2026, 3:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a38af81c16c81909e60702d8d3280c3 |
completed | June 22, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_6a037a069e6c8190857b611fffb7b867 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:07 p.m.