Triple
T33548101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SL Green Realty Corp. |
E859258
|
entity |
| Predicate | primaryPropertyUse |
P14072
|
FINISHED |
| Object | office |
—
|
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: office | Statement: [SL Green Realty Corp., primaryPropertyUse, office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPropertyUse Context triple: [SL Green Realty Corp., primaryPropertyUse, office]
-
A.
primaryProperty
Indicates that the referenced property is the main or most important attribute associated with an entity, typically preferred over other related properties.
-
B.
primaryLandUse
chosen
Indicates the main or dominant way in which a given piece of land is utilized or designated (e.g., residential, agricultural, commercial).
-
C.
primaryUseOf
Indicates that one entity serves as the main or principal function, purpose, or application of another entity.
-
D.
secondaryBuildingUse
Indicates how a building is used in a secondary or supplementary capacity in addition to its primary function.
-
E.
residenceUsedFor
Indicates that a particular residence is used for a specific purpose, function, or activity.
- 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_69f3497a5be08190a39b12736899e034 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:39 a.m.