Triple
T3370716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serpent Column |
E70946
|
entity |
| Predicate | approximateDateOfDedication |
P877
|
FINISHED |
| Object | 5th century BCE |
—
|
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: 5th century BCE | Statement: [Serpent Column, approximateDateOfDedication, 5th century BCE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateDateOfDedication Context triple: [Serpent Column, approximateDateOfDedication, 5th century BCE]
-
A.
dedicationDate
Indicates the date on which something (such as a building, monument, or work) is formally dedicated or inaugurated.
-
B.
rededicationDate
Indicates the date on which something is formally dedicated again, typically after restoration, change, or renewal.
-
C.
approximateYearOfCompletion
Indicates the estimated calendar year in which something was completed, rather than an exact or confirmed year.
-
D.
dateApproximate
chosen
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
E.
approximateStartYear
Indicates that the associated year value represents an estimated or imprecise starting year for an event, state, or relationship rather than an exact one.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2bb32f88190bacf50e11b50fe99 |
completed | March 8, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ada4317e288190ab7d0f66e9dba65f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.