Triple
T709833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin Beck Theatre |
E14180
|
entity |
| Predicate | hasMarquee |
P19074
|
FINISHED |
| Object | Broadway-style illuminated marquee |
—
|
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: Broadway-style illuminated marquee | Statement: [Martin Beck Theatre, hasMarquee, Broadway-style illuminated marquee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarquee Context triple: [Martin Beck Theatre, hasMarquee, Broadway-style illuminated marquee]
-
A.
hasMarker
Indicates that one entity possesses, is associated with, or is identified by a specific marker.
-
B.
hasBarrage
Indicates that one entity possesses, contains, or is equipped with a barrage (such as a concentrated, sustained sequence of attacks, shots, or similar actions).
-
C.
hasFullTextAvailableAt
Indicates that the complete text of a resource is accessible at a specified location or via a given link.
-
D.
hasFront
Indicates that an entity possesses or is associated with a front-facing side, surface, or portion.
-
E.
hasCurrent
Indicates that an entity presently possesses, exhibits, or is associated with a particular state, attribute, or resource at the current time.
- 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_69a493494ec48190ae6751683625a9ba |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5c011948190b2cfccd8fe722742 |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f0217081908268b3f47e72f8df |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a5bed20c81909ecc28bf42594e72 |
completed | March 1, 2026, 8:46 p.m. |
Created at: March 1, 2026, 7:36 p.m.