Triple
T26212920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isidore of Miletus |
E655536
|
entity |
| Predicate | roleInHagiaSophia |
P100182
|
FINISHED |
| Object | chief engineer |
—
|
LITERAL FINISHED |
How this triple was built (2 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: chief engineer | Statement: [Isidore of Miletus, roleInHagiaSophia, chief engineer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInHagiaSophia Context triple: [Isidore of Miletus, roleInHagiaSophia, chief engineer]
-
A.
roleInMosque
Indicates that an entity holds or performs a specific role, function, or position within a mosque.
-
B.
roleInConstantine
Indicates that an entity has a specific role or participation in the context of Constantine (e.g., in his life, reign, or related events or works).
-
C.
roleInMonument
chosen
Indicates that an entity holds or held a specific role, function, or contribution in relation to a particular monument.
-
D.
roleInMecca
Indicates that an entity holds or performs a specific role, function, or position in the context of Mecca.
-
E.
roleInKairouan
Indicates that an entity holds or held a specific role, position, or function in relation to Kairouan.
- F. None of above.
Provenance (3 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_69ee5b49adb4819086545280d4ef6337 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
Created at: April 26, 2026, 8:53 p.m.