Triple
T21209340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zeller Realty Group |
E522677
|
entity |
| Predicate | focusesOnStrategy |
P17512
|
FINISHED |
| Object | value-add office investments |
—
|
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: value-add office investments | Statement: [Zeller Realty Group, focusesOnStrategy, value-add office investments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnStrategy Context triple: [Zeller Realty Group, focusesOnStrategy, value-add office investments]
-
A.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
B.
campaignStrategyFocus
Indicates that a campaign’s strategic efforts are concentrated on a particular issue, audience, or approach.
-
C.
strategyEmphasis
chosen
Indicates an entity’s primary focus or priority within a broader strategy or plan.
-
D.
focusesOnSide
Indicates that an action, attention, or analysis is directed specifically toward one particular side or aspect of something.
-
E.
focusesOnTeam
Indicates that the subject directs attention, effort, or priority toward a particular team as the main area of concern 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73436eb4c819082e05caf1ba52672 |
completed | April 21, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69e5f6094e3c81909ee9699e00d371f7 |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:26 p.m.