Triple
T29728080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tour Avant-Seine |
E752237
|
entity |
| Predicate | clusterWith |
P143773
|
FINISHED |
| Object | other Front de Seine towers |
—
|
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: other Front de Seine towers | Statement: [Tour Avant-Seine, clusterWith, other Front de Seine towers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clusterWith Context triple: [Tour Avant-Seine, clusterWith, other Front de Seine towers]
-
A.
clusterPosition
Indicates the relative location or ordering of an element within a defined cluster or grouped set.
-
B.
coreCluster
Indicates that an entity belongs to, or is part of, a central or primary cluster within a larger grouping or structure.
-
C.
clusterCriterion
Indicates the rule or condition used to group items together into a cluster based on shared characteristics or similarity.
-
D.
groupOrCluster
chosen
Indicates that multiple entities are gathered together or associated as a single group or cluster based on some shared relation or proximity.
-
E.
hostCluster
Indicates a relationship where one cluster serves as the hosting or parent environment for another resource, service, or sub-cluster.
- 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_69f0d62a36a88190bf860f00da433ff8 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f673008bb081909623ca50205dc0a8 |
completed | May 2, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:40 p.m.