Triple
T29589930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montparnasse Tower complex |
E754123
|
entity |
| Predicate | hasPrimaryStructure |
P144577
|
FINISHED |
| Object | Tour Montparnasse office tower |
—
|
NE NERFINISHED |
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: Tour Montparnasse office tower | Statement: [Montparnasse Tower complex, hasPrimaryStructure, Tour Montparnasse office tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryStructure Context triple: [Montparnasse Tower complex, hasPrimaryStructure, Tour Montparnasse office tower]
-
A.
hasMainStructure
chosen
Indicates that one entity serves as the primary or central structural component of another entity.
-
B.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
C.
hasPrimaryConstituent
Indicates that one entity serves as the main or principal component, ingredient, or element of another entity.
-
D.
haveStructure
Indicates that an entity possesses a particular internal organization, arrangement, or structural composition.
-
E.
hasHumanStructure
Indicates that one entity possesses or exhibits a structural form or organization characteristic of humans.
- 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_69f0ef836ac88190bd809dc58b5ec907 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69ff84df768c81908c65a1a7e33103ad |
completed | May 9, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69ff848d0af881908ee42c27a58af47e |
completed | May 9, 2026, 7:01 p.m. |
Created at: April 28, 2026, 6:13 p.m.