Triple
T3803198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antoninus Pius |
E91738
|
entity |
| Predicate | deathPlace |
P21
|
FINISHED |
| Object |
Lorium
Lorium was an ancient Roman settlement along the Via Aurelia in Etruria, known as an imperial villa site associated with Emperor Antoninus Pius.
|
E387625
|
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: Lorium | Statement: [Antoninus Pius, deathPlace, Lorium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorium Context triple: [Antoninus Pius, deathPlace, Lorium]
-
A.
Pearre
Pearre is a given name used as the middle name of U.S. Air Force General Charles Pearre Cabell.
-
B.
Thaton
Thaton is an ancient city in southern Myanmar historically significant as a major center of the Mon kingdom and Theravada Buddhism in the region.
-
C.
Livermore
Livermore is a city in California’s Tri-Valley region known for its wine country, historic downtown, and proximity to major scientific research facilities.
-
D.
Avallon
Avallon is a historic commune in central France known for its medieval architecture and scenic location on a granite outcrop in the Burgundy region.
-
E.
Edenborn
Edenborn is a science fiction novel by Nick Sagan that continues his post-apocalyptic series exploring genetic engineering and the future of humanity.
- 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: Lorium Triple: [Antoninus Pius, deathPlace, Lorium]
Generated description
Lorium was an ancient Roman settlement along the Via Aurelia in Etruria, known as an imperial villa site associated with Emperor Antoninus Pius.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lorium Target entity description: Lorium was an ancient Roman settlement along the Via Aurelia in Etruria, known as an imperial villa site associated with Emperor Antoninus Pius.
-
A.
Pearre
Pearre is a given name used as the middle name of U.S. Air Force General Charles Pearre Cabell.
-
B.
Thaton
Thaton is an ancient city in southern Myanmar historically significant as a major center of the Mon kingdom and Theravada Buddhism in the region.
-
C.
Livermore
Livermore is a city in California’s Tri-Valley region known for its wine country, historic downtown, and proximity to major scientific research facilities.
-
D.
Avallon
Avallon is a historic commune in central France known for its medieval architecture and scenic location on a granite outcrop in the Burgundy region.
-
E.
Edenborn
Edenborn is a science fiction novel by Nick Sagan that continues his post-apocalyptic series exploring genetic engineering and the future of humanity.
- 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_69aed96354f48190a768966d6bd19b04 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee7bacf2881908198a77063d15d16 |
completed | March 9, 2026, 3:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f06889c88190ab4d8da7f0dfeadd |
completed | March 14, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_69b4f0e77efc8190b4459d4559261a2f |
completed | March 14, 2026, 5:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4f15cfde88190bcb2680b90f98111 |
completed | March 14, 2026, 5:25 a.m. |
Created at: March 9, 2026, 3:15 p.m.