Triple
T18156514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tabac |
E434644
|
entity |
| Predicate | spectatorCharacteristic |
P66775
|
FINISHED |
| Object | harbor-side viewing area |
—
|
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: harbor-side viewing area | Statement: [Tabac, spectatorCharacteristic, harbor-side viewing area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spectatorCharacteristic Context triple: [Tabac, spectatorCharacteristic, harbor-side viewing area]
-
A.
spectatorType
Indicates the role or category of a spectator in relation to an event or activity.
-
B.
spectatorProfile
chosen
Indicates a relationship where one entity serves as or defines the viewing or audience-oriented characteristics, preferences, or behavior profile of another entity.
-
C.
spectatorInterest
Indicates that one entity has an interest in observing, watching, or following another entity or event as a spectator.
-
D.
spectatorAppeal
Indicates that an action, event, or entity is appealing, entertaining, or attractive to spectators or an audience.
-
E.
spectatorsFrom
Indicates that one or more spectators originate from, are associated with, or come to an event from a particular place or source.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4debe27a88190bd76c6f78fcf1bd1 |
completed | April 19, 2026, 1:55 p.m. |
| PD | Predicate disambiguation | batch_69e4331baeb88190b21f50a98c36c78e |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:30 a.m.