Triple
T13837371
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barrières of Paris |
E332565
|
entity |
| Predicate | someElementsStillExistAs |
P89335
|
FINISHED |
| Object | historic monuments |
—
|
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: historic monuments | Statement: [Barrières of Paris, someElementsStillExistAs, historic monuments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: someElementsStillExistAs Context triple: [Barrières of Paris, someElementsStillExistAs, historic monuments]
-
A.
stillExists
Indicates that the referenced entity continues to exist or remain in effect at the current point in time.
-
B.
hasSurvivingElement
chosen
Indicates that an entity retains at least one remaining or extant part, instance, or component that still exists.
-
C.
existsIf
Indicates that the existence or validity of one entity or condition depends on the presence or truth of another specified condition.
-
D.
stillUsedBy
Indicates that something continues to be used or relied upon by another entity at the present time.
-
E.
existsFor
Indicates that something is present, available, or holds true for a particular entity, context, 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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02ac6b7c81908d44632d6d628339 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.