Triple
T157011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ancient Greek religion |
E3200
|
entity |
| Predicate | hasReligiousSpecialist |
P3092
|
FINISHED |
| Object | mantis |
—
|
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: mantis | Statement: [Ancient Greek religion, hasReligiousSpecialist, mantis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReligiousSpecialist Context triple: [Ancient Greek religion, hasReligiousSpecialist, mantis]
-
A.
hasClergyType
chosen
Indicates the specific category or role of clergy associated with an entity.
-
B.
hasClergyOrder
Indicates that an entity is associated with, or belongs to, a specific religious or clerical order.
-
C.
hasClericalDiscipline
Indicates that an entity is subject to, or governed by, a particular set of clerical or religious disciplinary rules or practices.
-
D.
hasSpecialty
Indicates that an entity possesses a particular area of expertise, focus, or professional specialization.
-
E.
hasReligiousSite
Indicates that a location or entity possesses, contains, or is associated with a religious site such as a temple, church, mosque, shrine, or similar place of worship.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a25830136881909f5ecb2cb22097b2 |
completed | Feb. 28, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69a2565f30848190a2a71fdb7dc140b5 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.