Triple
T22012102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UTC@harbourside |
E543601
|
entity |
| Predicate | intendedIntake |
P146269
|
FINISHED |
| Object | students from Newhaven |
—
|
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: students from Newhaven | Statement: [UTC@harbourside, intendedIntake, students from Newhaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedIntake Context triple: [UTC@harbourside, intendedIntake, students from Newhaven]
-
A.
intake
Indicates the act of taking something in or consuming it, such as food, drink, or other substances, into a system or organism.
-
B.
intendedFood
Indicates that one entity is the food item that another entity plans or is meant to eat or consume.
-
C.
intendedToServe
Indicates that one entity was designed, planned, or purposed specifically to benefit, assist, or fulfill the needs of another entity.
-
D.
intakeLocation
Indicates the place or facility where an entity is initially received, admitted, or taken in.
-
E.
intendsTo
Indicates that one entity has the purpose, plan, or desire to perform an action involving another entity or outcome.
- F. None of above. chosen
Provenance (4 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a520bc8190865f525a87255fb2 |
completed | April 28, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69e6f62dc9d88190ae387f145f9528de |
completed | April 21, 2026, 3:59 a.m. |
| PDg | Predicate description generation | batch_69e6fad4a540819096cdd5ea08527220 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 8:22 p.m.