Triple
T22718888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Esagila tablet |
E561806
|
entity |
| Predicate | religiousSiteDescribed |
P34373
|
FINISHED |
| Object | main temple of Marduk in Babylon |
—
|
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: main temple of Marduk in Babylon | Statement: [Esagila tablet, religiousSiteDescribed, main temple of Marduk in Babylon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousSiteDescribed Context triple: [Esagila tablet, religiousSiteDescribed, main temple of Marduk in Babylon]
-
A.
religiousSiteType
chosen
Indicates the specific kind or category of religious site associated with an entity (e.g., church, mosque, temple).
-
B.
religiousSiteRank
Indicates the hierarchical or status-based rank assigned to a religious site within a religious or organizational structure.
-
C.
isPlaceOfPilgrimageFor
Indicates that a location serves as a destination for religious or spiritual pilgrimage for a person or group.
-
D.
nearReligiousSite
Indicates that one entity is located close to or in the immediate vicinity of a religious site.
-
E.
religiousSiteAffected
Indicates that a religious site is impacted or influenced by a particular event, action, or condition.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1790fbf9c819082ba7b48801a7b39 |
completed | April 29, 2026, 3:20 a.m. |
| PD | Predicate disambiguation | batch_69eed2a971c0819088af574e40c9343f |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:19 p.m.