Triple
T36889695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pillar of Eliseg |
E911709
|
entity |
| Predicate | inscriptionCondition |
P186648
|
FINISHED |
| Object | faded |
—
|
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: faded | Statement: [Pillar of Eliseg, inscriptionCondition, faded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inscriptionCondition Context triple: [Pillar of Eliseg, inscriptionCondition, faded]
-
A.
inscriptionFormula
Indicates that one entity bears or contains a specific inscribed text, phrase, or formula associated with it.
-
B.
inscriptionMode
Indicates the method or technique by which an inscription is created, applied, or recorded on a surface or medium.
-
C.
inscription
Indicates that text has been written, carved, or engraved onto a surface or object.
-
D.
inscriptionSupport
Indicates that one entity serves as the physical surface or material on which another entity (an inscription) is written, carved, or otherwise recorded.
-
E.
inscriptionBy
Indicates that an inscription was created, written, or carved by a particular agent or entity.
- F. None of above. chosen
Provenance (4 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_69f76e8335908190b77e7e11d0e80820 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fe1a1ca4819084c196f0041f0be2 |
completed | May 5, 2026, 2:26 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
| PDg | Predicate description generation | batch_69f9fd66eed48190bdc26a8def328c2d |
completed | May 5, 2026, 2:23 p.m. |
Created at: May 3, 2026, 4:13 p.m.