Triple
T1252446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arch of Titus |
E26906
|
entity |
| Predicate | originallyHad |
P25840
|
FINISHED |
| Object | bronze quadriga statue on top |
—
|
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: bronze quadriga statue on top | Statement: [Arch of Titus, originallyHad, bronze quadriga statue on top]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originallyHad Context triple: [Arch of Titus, originallyHad, bronze quadriga statue on top]
-
A.
originallyIn
Indicates that something first appeared, was created, or was initially located within a particular context, source, or place.
-
B.
wasOriginally
Indicates that an entity had a particular state, form, type, or affiliation at an earlier time, which has since changed.
-
C.
originallyCoveredBy
Indicates that something was first protected, reported on, or documented by a particular source, medium, or entity before any others.
-
D.
hadFort
Indicates that an entity possessed, controlled, or contained a fort at some time.
-
E.
has
Indicates that one entity possesses, owns, contains, or includes another entity as part of its state or composition.
- 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_69a49487a9c48190ba9b05348fd1b53f |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf875cf48190b6781d41097ee39b |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6c977c8190a2bf3e8b67a59beb |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bc49693c8190978ec63a5171d342 |
completed | March 1, 2026, 10:23 p.m. |
Created at: March 1, 2026, 7:47 p.m.