Triple
T29539877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Island of Terror |
E749461
|
entity |
| Predicate | narrativeLocation |
P40
|
FINISHED |
| Object |
fictional Petrie Island
Fictional Petrie Island is an invented island setting that serves as the isolated, suspenseful backdrop for the events of the horror film "Island of Terror."
|
E1871166
|
NE 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: fictional Petrie Island | Statement: [Island of Terror, narrativeLocation, fictional Petrie Island]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: fictional Petrie Island Triple: [Island of Terror, narrativeLocation, fictional Petrie Island]
Generated description
Fictional Petrie Island is an invented island setting that serves as the isolated, suspenseful backdrop for the events of the horror film "Island of Terror."
Provenance (5 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_69f0bd47abb081909bd6e6a33d770fd8 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66cc9c11c8190b2d06ced137ec777 |
completed | May 2, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a260c3a98c48190b89071db597a1787 |
completed | June 8, 2026, 12:26 a.m. |
| NEDg | Description generation | batch_6a26101eb69481909e5a27c1fd3791f0 |
completed | June 8, 2026, 12:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a26142129608190b8028efd1baf9f50 |
completed | June 8, 2026, 1 a.m. |
Created at: April 28, 2026, 5:01 p.m.